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. 34661
    Prev
    Next
    INDEX
    Explanations

    news captions related to protests and events happening in various locations

    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
    +0.14
    0.7%
    378
    +0.12
    0.6%
    321
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.14
    -0.05
    31
    +0.12
    0.12
    488
    +0.11
    0.12
    Negative Logits
    shapeshifter
    -0.66
     Enlightenment
    -0.63
    ulative
    -0.60
    netflix
    -0.60
     denial
    -0.59
    sed
    -0.59
    volume
    -0.58
    stood
    -0.57
    termin
    -0.57
     conversion
    -0.56
    POSITIVE LOGITS
     caption
    0.72
    taboola
    0.72
    VERTISEMENT
    0.68
     IMAGES
    0.66
    embed
    0.65
     Photos
    0.63
    endant
    0.62
     embed
    0.62
    VERTIS
    0.61
    anche
    0.61
    Activations Density 8.655%

    No Known Activations