© 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. 32643
    Prev
    Next
    INDEX
    Explanations

    questions or requests for information within a text, often related to personal details or processes

    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
    +0.21
    0.9%
    113
    +0.13
    0.5%
    679
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    119
    +0.21
    0.10
    70
    +0.13
    0.10
    113
    +0.10
    0.07
    Negative Logits
    ufact
    -0.84
     Hots
    -0.83
    Church
    -0.79
    ña
    -0.78
     ç¥ŀ
    -0.76
    bold
    -0.75
    ãĥĨãĤ£
    -0.73
    SAY
    -0.71
    odic
    -0.71
    ãĥĢ
    -0.70
    POSITIVE LOGITS
    etts
    0.94
    lists
    0.92
    boxes
    0.90
    ysis
    0.89
    mate
    0.88
    ups
    0.83
    list
    0.83
    ers
    0.79
    ARDS
    0.79
    box
    0.78
    Activations Density 5.392%

    No Known Activations