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. 34293
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically 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
    447
    +0.15
    0.7%
    288
    +0.13
    0.7%
    696
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.20
    326
    +0.13
    0.18
    151
    +0.10
    0.13
    Negative Logits
    ered
    -0.71
    ongyang
    -0.70
    ering
    -0.66
    resent
    -0.66
    rogen
    -0.66
    ple
    -0.66
    racted
    -0.66
    ramid
    -0.66
    href
    -0.64
    pled
    -0.63
    POSITIVE LOGITS
     Ashe
    0.97
     Weasley
    0.93
     Pend
    0.83
     Conan
    0.81
    andise
    0.76
     Arthur
    0.75
    itic
    0.72
     Dent
    0.69
    ufact
    0.68
    beit
    0.66
    Activations Density 5.618%

    No Known Activations