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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 34813
    Prev
    Next
    INDEX
    Explanations

    dates and numbers in a non-fictional context

    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
    +0.17
    0.8%
    421
    +0.11
    0.5%
    655
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    561
    +0.17
    0.09
    390
    +0.11
    0.04
    421
    +0.10
    0.07
    Negative Logits
    hap
    -0.72
    yip
    -0.69
    ickr
    -0.69
    gur
    -0.68
    lime
    -0.68
     fung
    -0.65
     gloves
    -0.65
    ertodd
    -0.64
    ITNESS
    -0.64
    vation
    -0.62
    POSITIVE LOGITS
     protagonist
    0.96
     satir
    0.92
     synopsis
    0.90
     loosely
    0.90
     narrator
    0.89
    Synopsis
    0.87
     premiered
    0.85
     actresses
    0.85
     storylines
    0.85
     actress
    0.85
    Activations Density 8.865%

    No Known Activations