© 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. 36120
    Prev
    Next
    INDEX
    Explanations

    proper nouns and acronyms in financial and political contexts

    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
    575
    +0.10
    0.5%
    718
    +0.10
    0.5%
    187
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.23
    575
    +0.10
    0.15
    401
    +0.09
    0.11
    Negative Logits
    hold
    -0.72
     Alchemist
    -0.69
    swick
    -0.69
    ãĤ¤ãĥĪ
    -0.67
    gary
    -0.67
    vier
    -0.65
     Universities
    -0.61
    quished
    -0.60
    obyl
    -0.59
    ãĤ¨ãĥ«
    -0.58
    POSITIVE LOGITS
    odcast
    0.83
    raction
    0.81
    aired
    0.78
    ongyang
    0.75
    ixel
    0.74
    ython
    0.72
    ools
    0.71
    airs
    0.70
    arser
    0.70
    unction
    0.70
    Activations Density 8.639%

    No Known Activations