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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 34122
    Prev
    Next
    INDEX
    Explanations

    references to financial institutions and economic concepts such as investments and profitability

    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
    +0.15
    0.7%
    631
    +0.10
    0.4%
    589
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    119
    +0.15
    0.13
    442
    +0.10
    0.08
    640
    +0.10
    0.26
    Negative Logits
    isconsin
    -0.72
    xit
    -0.72
    pta
    -0.63
    abama
    -0.63
    ajor
    -0.62
    owder
    -0.62
    rocal
    -0.62
    othal
    -0.62
     Ambro
    -0.62
    psc
    -0.61
    POSITIVE LOGITS
     (>
    0.75
     lumber
    0.72
    Thumbnail
    0.68
    adin
    0.67
    bang
    0.67
     è£ıè
    0.66
     Bust
    0.66
    Winged
    0.65
     Bundle
    0.64
    ortment
    0.64
    Activations Density 17.243%

    No Known Activations