© 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 EvalsExportsAPI 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 12568
    Prev
    Next
    INDEX
    Explanations

    fantasy creatures and elements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    481
    +0.20
    0.9%
    447
    +0.17
    0.8%
    231
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    140
    +0.20
    0.02
    545
    +0.17
    0.02
    373
    +0.11
    -0.01
    Negative Logits
    ometimes
    -0.76
    bill
    -0.74
    xit
    -0.72
    Percent
    -0.71
    negie
    -0.70
    avorite
    -0.68
     Bland
    -0.68
    è£ħ
    -0.67
    ãĥ¼ãĥĨãĤ£
    -0.66
    abase
    -0.66
    POSITIVE LOGITS
     Entered
    0.77
     Lair
    0.70
    engu
    0.68
     armour
    0.68
     Casting
    0.68
    azaar
    0.67
     Slime
    0.66
    roach
    0.66
     Execution
    0.66
     Orc
    0.65
    Activations Density 0.076%

    No Known Activations