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. 4227
    Prev
    Next
    INDEX
    Explanations

    people's names

    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
    497
    +0.15
    0.7%
    274
    +0.12
    0.6%
    718
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.25
    326
    +0.12
    0.23
    709
    +0.11
    0.11
    Negative Logits
    cedes
    -0.71
    ãĤ¹ãĥĪ
    -0.68
    ãĤº
    -0.63
    ãĥ¼ãĥĨ
    -0.63
    ths
    -0.61
    ãĤ´ãĥ³
    -0.61
    rawdownloadcloneembedreportprint
    -0.60
    ça
    -0.60
    ãĥ¼ãĤ¯
    -0.59
    cedented
    -0.58
    POSITIVE LOGITS
    older
    0.73
    iets
    0.71
    VM
    0.67
    aceae
    0.66
    itt
    0.65
    ency
    0.65
    govtrack
    0.64
    etta
    0.64
    enger
    0.63
    oba
    0.63
    Activations Density 8.406%

    No Known Activations