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. 45294
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "hop"

    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
    +0.16
    0.8%
    526
    +0.13
    0.7%
    288
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.16
    0.12
    485
    +0.13
    0.10
    623
    +0.12
    0.06
    Negative Logits
     payable
    -0.73
    ateral
    -0.67
     confir
    -0.58
    ISE
    -0.57
     conclud
    -0.57
    Downloadha
    -0.57
     bundled
    -0.56
     withd
    -0.56
     reconc
    -0.56
    $$$$
    -0.56
    POSITIVE LOGITS
    eful
    1.10
    Hop
    1.06
    efully
    0.93
    lite
    0.90
     Hop
    0.84
    retty
    0.82
    hop
    0.80
    sticks
    0.78
     hop
    0.78
    along
    0.78
    Activations Density 8.008%

    No Known Activations