© 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. 45947
    Prev
    Next
    INDEX
    Explanations

    communication tools and platforms

    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
    481
    +0.12
    0.6%
    564
    +0.12
    0.5%
    429
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.12
    0.15
    564
    +0.12
    0.12
    756
    +0.10
    -0.14
    Negative Logits
     revenge
    -0.72
     Happiness
    -0.69
    reprene
    -0.66
    iasis
    -0.64
     voic
    -0.63
     happier
    -0.62
     Quote
    -0.62
     manifesto
    -0.61
    ews
    -0.60
    spir
    -0.58
    POSITIVE LOGITS
    quickShipAvailable
    0.74
     partName
    0.72
     "$:/
    0.71
    available
    0.67
     credentials
    0.65
     calibrated
    0.64
     restraints
    0.63
     Adobe
    0.63
    ournal
    0.63
    isoft
    0.63
    Activations Density 10.173%

    No Known Activations