© 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. 33939
    Prev
    Next
    INDEX
    Explanations

    items in a list

    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
    222
    +0.11
    0.6%
    167
    +0.11
    0.5%
    69
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.16
    326
    +0.11
    0.17
    485
    +0.10
    0.08
    Negative Logits
    birth
    -0.69
    displayText
    -0.60
    BUS
    -0.58
     Aber
    -0.58
    IL
    -0.57
    wav
    -0.56
     Equality
    -0.55
    forth
    -0.55
     lat
    -0.55
    perty
    -0.55
    POSITIVE LOGITS
    ening
    1.35
    eners
    1.11
    ened
    1.06
    ener
    1.03
    ing
    0.90
    erv
    0.80
    ensen
    0.78
    enhagen
    0.74
    geist
    0.74
    enf
    0.74
    Activations Density 5.105%

    No Known Activations