© 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. 33836
    Prev
    Next
    INDEX
    Explanations

    sections or summaries within a document

    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
    195
    +0.07
    0.6%
    447
    +0.05
    0.5%
    274
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.07
    0.11
    288
    +0.05
    0.20
    575
    +0.05
    0.15
    Negative Logits
    Fish
    -0.42
    mouth
    -0.41
    vey
    -0.39
    ench
    -0.37
    weather
    -0.37
    immune
    -0.35
    inence
    -0.35
    thing
    -0.35
    ldon
    -0.35
    hammad
    -0.35
    POSITIVE LOGITS
    ital
    0.49
    ilitation
    0.40
     recap
    0.40
    apse
    0.40
    amera
    0.39
    olitan
    0.37
    ITAL
    0.37
    apses
    0.36
     timeline
    0.36
    PsyNetMessage
    0.34
    Activations Density 6.591%

    No Known Activations