© 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. 14065
    Prev
    Next
    INDEX
    Explanations

    monetary values mentioned in the text

    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
    +0.19
    0.8%
    63
    +0.11
    0.5%
    241
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.19
    0.11
    344
    +0.11
    0.10
    165
    +0.11
    0.05
    Negative Logits
    alys
    -0.85
    soType
    -0.81
    sole
    -0.80
    warts
    -0.78
    agn
    -0.76
     Aval
    -0.75
    umbn
    -0.72
    strength
    -0.70
    imes
    -0.69
    ormal
    -0.68
    POSITIVE LOGITS
    -$
    1.33
    /$
    1.04
     USD
    1.03
     apiece
    0.98
     (£
    0.97
     annually
    0.93
     dollars
    0.90
     per
    0.87
     worth
    0.86
    +.
    0.83
    Activations Density 7.312%

    No Known Activations