© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 31524
    Prev
    Next
    INDEX
    Explanations

    financial and statistical information in a text, especially related to earnings, taxes, and business deals

    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
    637
    +0.02
    0.5%
    684
    +0.02
    0.5%
    412
    +0.02
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.02
    0.15
    36
    +0.02
    0.15
    344
    +0.02
    0.13
    Negative Logits
    utters
    -0.17
    breaks
    -0.17
    simple
    -0.16
    breakers
    -0.16
    uers
    -0.16
    aband
    -0.15
    rave
    -0.15
    ingers
    -0.15
    ards
    -0.14
    itives
    -0.14
    POSITIVE LOGITS
    éĹ
    0.16
     average
    0.15
     NYPD
    0.14
     effort
    0.14
     total
    0.14
     blackout
    0.14
    éŃĶ
    0.14
     tally
    0.14
    ICA
    0.14
    ãĥ©ãĥ³
    0.13
    Activations Density 6.175%

    No Known Activations