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. 13447
    Prev
    Next
    INDEX
    Explanations

    chemical and molecular structure representations

    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
    558
    +0.12
    0.5%
    447
    +0.11
    0.5%
    275
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.12
    0.11
    186
    +0.11
    0.08
    368
    +0.11
    0.13
    Negative Logits
     defect
    -0.72
    gotten
    -0.69
     keyword
    -0.67
     immediate
    -0.66
     Eisenhower
    -0.66
    ItemThumbnailImage
    -0.65
    displayText
    -0.64
     advertisers
    -0.63
    ktop
    -0.63
     ambush
    -0.62
    POSITIVE LOGITS
    Äĩ
    0.97
    merce
    0.94
    uchi
    0.87
    士
    0.87
    rencies
    0.86
    ondo
    0.85
    arta
    0.84
    asma
    0.83
    nova
    0.81
    quit
    0.81
    Activations Density 22.611%

    No Known Activations