© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 35769
    Prev
    Next
    INDEX
    Explanations

    historical narratives and biographical accounts, particularly focusing on individuals' actions and achievements in various contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    277
    +0.10
    0.5%
    646
    +0.10
    0.5%
    226
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    555
    +0.10
    0.07
    261
    +0.10
    0.06
    582
    +0.08
    0.03
    Negative Logits
    "]=>
    -0.71
    abin
    -0.70
    iggurat
    -0.60
    ribe
    -0.58
     EM
    -0.57
    sembly
    -0.57
    enges
    -0.57
     GOT
    -0.57
    endered
    -0.57
    "},
    -0.57
    POSITIVE LOGITS
    Lenin
    0.63
    ãĥ³ãĤ¸
    0.61
     intending
    0.61
    math
    0.61
     exhausted
    0.59
     Frie
    0.59
     Cous
    0.58
     aback
    0.57
     accustomed
    0.57
     restless
    0.57
    Activations Density 10.600%

    No Known Activations