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. 34332
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of people

    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
    288
    +0.11
    0.6%
    453
    +0.11
    0.6%
    430
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.17
    288
    +0.11
    0.18
    453
    +0.10
    0.09
    Negative Logits
    Edited
    -0.64
    wart
    -0.64
    adesh
    -0.62
    izoph
    -0.60
    itbart
    -0.60
    agnetic
    -0.60
    bell
    -0.59
    anooga
    -0.57
    cffffcc
    -0.56
    ãĤ´ãĥ³
    -0.56
    POSITIVE LOGITS
    oso
    0.80
     Vincent
    0.72
     Scully
    0.71
    rette
    0.64
     Leone
    0.63
    inho
    0.63
     Vaughn
    0.60
     Kart
    0.60
    oshenko
    0.59
     Foster
    0.58
    Activations Density 5.051%

    No Known Activations