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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 34563
    Prev
    Next
    INDEX
    Explanations

    French words with accents and special characters, particularly related to art and creation

    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
    320
    +0.10
    0.5%
    365
    +0.10
    0.5%
    515
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    555
    +0.10
    0.09
    659
    +0.10
    0.09
    545
    +0.09
    0.06
    Negative Logits
    ISM
    -0.74
    SHIP
    -0.72
    ancial
    -0.70
     boiler
    -0.62
    ariat
    -0.62
     ---------
    -0.61
    è»
    -0.61
    istically
    -0.61
    ItemTracker
    -0.61
    >>\
    -0.60
    POSITIVE LOGITS
    earchers
    1.11
    terday
    1.05
    hiba
    1.01
    ktop
    0.88
    cul
    0.85
    quer
    0.85
    bians
    0.84
    oteric
    0.84
    earch
    0.83
    pect
    0.82
    Activations Density 6.653%

    No Known Activations