© 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. 36195
    Prev
    Next
    INDEX
    Explanations

    terms associated with influential and defining aspects or entities within a particular context

    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
    219
    +0.09
    0.5%
    639
    +0.08
    0.5%
    497
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.09
    0.14
    362
    +0.08
    0.10
    210
    +0.08
    0.06
    Negative Logits
    hops
    -0.77
    ruary
    -0.66
    peak
    -0.66
    asus
    -0.66
    otiation
    -0.64
    eva
    -0.64
    ngth
    -0.61
    paio
    -0.61
    Jump
    -0.61
    termination
    -0.60
    POSITIVE LOGITS
     factor
    0.75
     characteristic
    0.69
     influence
    0.65
     realization
    0.64
     theme
    0.64
     mechanism
    0.63
     testament
    0.59
     effect
    0.59
     indicator
    0.58
     tendency
    0.58
    Activations Density 8.711%

    No Known Activations