Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 34327
    Prev
    Next
    INDEX
    Explanations

    words related to protein electrophoresis techniques and medical conditions like fibrosis and cardiac features

    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
    569
    +0.12
    0.6%
    71
    +0.11
    0.5%
    288
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.18
    99
    +0.11
    0.10
    11
    +0.11
    0.06
    Negative Logits
    ndra
    -0.77
    eer
    -0.73
    pend
    -0.69
    zag
    -0.67
    FUL
    -0.64
     Nuggets
    -0.63
    creen
    -0.62
     Furious
    -0.60
    ãĥ´
    -0.59
     Advent
    -0.58
    POSITIVE LOGITS
    obic
    1.06
    obia
    1.04
    ysics
    0.93
    ysical
    0.87
    osate
    0.87
    osph
    0.87
    otos
    0.86
    atform
    0.82
    roph
    0.80
    otics
    0.80
    Activations Density 5.462%

    No Known Activations