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. 4592
    Prev
    Next
    INDEX
    Explanations

    physical body parts, particularly hands, in various contexts

    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
    174
    +0.08
    0.5%
    688
    +0.08
    0.5%
    605
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    174
    +0.08
    0.06
    109
    +0.08
    0.07
    288
    +0.07
    0.13
    Negative Logits
     Modes
    -0.60
    nih
    -0.55
    hiba
    -0.55
    ascus
    -0.54
    COMPLE
    -0.49
    mingham
    -0.48
    nel
    -0.48
    chid
    -0.48
    CENT
    -0.47
    necess
    -0.47
    POSITIVE LOGITS
    maid
    0.56
    bag
    0.52
     franch
    0.51
     bearer
    0.49
     shake
    0.47
     merch
    0.47
    picked
    0.46
     jerk
    0.43
     arming
    0.43
    onica
    0.43
    Activations Density 3.211%

    No Known Activations