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

    Neuronpedia

    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 Local
    9. 6-RES_SCL-AJT
    11. 3664
    Prev
    Next
    INDEX
    Explanations

    information related to job experiences and personal accomplishments

    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
    447
    +0.34
    1.8%
    481
    +0.20
    1.0%
    653
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    351
    +0.34
    0.10
    481
    +0.20
    0.49
    393
    +0.08
    0.51
    Negative Logits
    hovah
    -0.63
    raf
    -0.62
    ourke
    -0.62
    habi
    -0.60
    ãĥ¯
    -0.60
    azeera
    -0.59
    xit
    -0.59
    eware
    -0.58
     awaits
    -0.55
    otin
    -0.55
    POSITIVE LOGITS
     hadn
    0.63
    ranged
    0.63
     Soviets
    0.62
     lacked
    0.62
     Ended
    0.60
     tended
    0.58
     Voldemort
    0.58
     Weasley
    0.58
     Anim
    0.57
     smelled
    0.56
    Activations Density 41.462%

    No Known Activations