© 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. 4825
    Prev
    Next
    INDEX
    Explanations

    code and technical operations within a software development 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
    447
    +0.27
    1.4%
    314
    +0.16
    0.8%
    727
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.27
    -0.02
    585
    +0.16
    0.20
    727
    +0.08
    0.11
    Negative Logits
     �
    -0.68
     biod
    -0.64
    .","
    -0.63
    ��
    -0.58
     guiActiveUnfocused
    -0.56
    "}],"
    -0.56
    "},"
    -0.56
     liqu
    -0.55
     |--
    -0.55
    "],"
    -0.53
    POSITIVE LOGITS
    resa
    0.82
    odore
    0.77
    swers
    0.75
    trak
    0.74
    aples
    0.73
    enhagen
    0.69
    mosp
    0.69
    cloneembedreportprint
    0.69
    pherd
    0.68
    phabet
    0.67
    Activations Density 30.123%

    No Known Activations