© 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. 14059
    Prev
    Next
    INDEX
    Explanations

    mentions of "guest" in documents

    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
    640
    +0.03
    0.6%
    195
    +0.03
    0.5%
    341
    +0.03
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    644
    +0.03
    0.08
    195
    +0.03
    0.01
    310
    +0.03
    0.07
    Negative Logits
     BET
    -0.22
    cale
    -0.21
    ments
    -0.21
    hest
    -0.20
    utics
    -0.19
     Yard
    -0.19
    ione
    -0.18
    xual
    -0.18
    inness
    -0.18
    ptives
    -0.18
    POSITIVE LOGITS
    Guest
    0.28
    abor
    0.20
    Writer
    0.20
     notebook
    0.20
    inar
    0.19
    cedes
    0.19
    ________________
    0.19
    ãģķ
    0.18
    uler
    0.18
     dose
    0.18
    Activations Density 3.996%

    No Known Activations