© 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. 36606
    Prev
    Next
    INDEX
    Explanations

    company names, particularly those related to telecommunication and technology

    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
    146
    +0.12
    0.5%
    247
    +0.11
    0.5%
    43
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.12
    0.06
    2
    +0.11
    0.03
    241
    +0.11
    0.05
    Negative Logits
     vomiting
    -0.79
     prol
    -0.78
     ballet
    -0.73
     juveniles
    -0.73
    erva
    -0.73
     pupils
    -0.73
     diam
    -0.71
     lucid
    -0.70
     blur
    -0.70
    blance
    -0.69
    POSITIVE LOGITS
    Wan
    0.92
    amacare
    0.88
    tin
    0.88
    ahn
    0.86
    tis
    0.86
    Sax
    0.85
    IB
    0.85
    TA
    0.84
    NI
    0.83
    Store
    0.83
    Activations Density 4.048%

    No Known Activations