© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 35286
    Prev
    Next
    INDEX
    Explanations

    information related to historical and biographical narratives, specifically focusing on personal stories and events

    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
    494
    +0.15
    0.7%
    305
    +0.11
    0.5%
    475
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    360
    +0.15
    0.12
    566
    +0.11
    0.10
    663
    +0.10
    0.08
    Negative Logits
    "},"
    -0.65
    \":
    -0.65
    ashes
    -0.65
     coordinating
    -0.63
     apprehens
    -0.62
     targeting
    -0.61
    ashing
    -0.60
     multipl
    -0.59
     staging
    -0.58
     aiming
    -0.58
    POSITIVE LOGITS
    remember
    0.80
     remember
    0.73
    yond
    0.73
    ury
    0.69
     hindsight
    0.69
    soType
    0.69
     ital
    0.68
    Legend
    0.66
     remem
    0.66
    nan
    0.65
    Activations Density 9.922%

    No Known Activations