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

    Neuronpedia

    APICircuit 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. 13354
    Prev
    Next
    INDEX
    Explanations

    expressions of praise or approval within longer text passages

    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
    +0.11
    0.6%
    669
    +0.10
    0.5%
    536
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.11
    0.30
    142
    +0.10
    0.13
    283
    +0.09
    -0.01
    Negative Logits
    thur
    -0.63
    pora
    -0.60
    acho
    -0.58
    VT
    -0.56
     TM
    -0.54
    atl
    -0.53
    UA
    -0.52
     thor
    -0.51
    opers
    -0.50
    iframe
    -0.50
    POSITIVE LOGITS
    nered
    0.75
    dden
    0.67
    itud
    0.67
    gre
    0.62
    structed
    0.61
    umenthal
    0.61
    rand
    0.61
    ubric
    0.59
    stood
    0.56
    kered
    0.54
    Activations Density 15.347%

    No Known Activations