Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4459
    Prev
    Next
    INDEX
    Explanations

    references to various locations being described as "home."

    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
    +0.20
    0.9%
    152
    +0.13
    0.6%
    270
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    270
    +0.20
    0.06
    365
    +0.13
    0.04
    152
    +0.12
    0.10
    Negative Logits
    andum
    -0.91
    uel
    -0.77
    terday
    -0.77
    uary
    -0.76
    ongyang
    -0.75
    undo
    -0.72
    uality
    -0.71
    veyard
    -0.69
    abwe
    -0.68
    asm
    -0.68
    POSITIVE LOGITS
    coming
    1.07
    opathy
    1.00
    opathic
    0.97
    grown
    0.97
    pun
    0.95
    brew
    0.94
    nikov
    0.93
    opath
    0.90
    buy
    0.87
    chool
    0.82
    Activations Density 6.133%

    No Known Activations