© 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. 32315
    Prev
    Next
    INDEX
    Explanations

    mentions of companies and financial information

    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
    +0.28
    1.2%
    114
    +0.11
    0.5%
    361
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.28
    0.36
    283
    +0.11
    -0.00
    149
    +0.11
    0.05
    Negative Logits
     severity
    -0.75
    jury
    -0.74
    hyde
    -0.72
     gore
    -0.69
    geries
    -0.69
     recess
    -0.69
     readings
    -0.69
    ilation
    -0.69
     endings
    -0.68
     "$:/
    -0.68
    POSITIVE LOGITS
     subsidiaries
    1.48
     headquartered
    1.39
     subsidiary
    1.25
    DAQ
    1.19
     Ltd
    1.12
     Holdings
    1.08
     Alibaba
    1.05
     IPO
    1.05
     CEO
    1.04
     shareholder
    1.03
    Activations Density 19.919%

    No Known Activations