© 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. 12742
    Prev
    Next
    INDEX
    Explanations

    scientific articles from journals

    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
    +0.10
    0.6%
    146
    +0.09
    0.6%
    314
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.10
    0.15
    640
    +0.09
    0.25
    765
    +0.07
    0.13
    Negative Logits
    plet
    -0.53
    condition
    -0.48
    express
    -0.48
     sleeper
    -0.48
    iple
    -0.48
    yond
    -0.48
     experien
    -0.47
     separ
    -0.46
    ãĥij
    -0.45
     BUS
    -0.45
    POSITIVE LOGITS
    Newsletter
    0.62
    Enlarge
    0.53
     Conference
    0.48
     Commissioners
    0.48
    ":["
    0.48
    ingham
    0.47
    ozo
    0.47
     Eug
    0.47
     Appropriations
    0.46
     Appeals
    0.46
    Activations Density 11.118%

    No Known Activations