© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 33644
    Prev
    Next
    INDEX
    Explanations

    the word "roll" or phrases related to rolling actions or mechanisms

    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
    +0.18
    0.7%
    274
    +0.15
    0.6%
    622
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.18
    0.40
    138
    +0.15
    0.39
    64
    +0.15
    -0.13
    Negative Logits
    ãĥ¤
    -1.10
    ãĤ»
    -0.96
    bub
    -0.93
    ãĥŁ
    -0.91
    orial
    -0.89
    ILE
    -0.88
    ãĤ±
    -0.87
    perse
    -0.86
    ilities
    -0.86
    acters
    -0.85
    POSITIVE LOGITS
    sheet
    1.08
     downhill
    1.04
    roll
    1.04
    Roll
    1.01
    aways
    1.00
    back
    0.99
    outs
    0.98
    anut
    0.96
     roll
    0.94
     rolling
    0.94
    Activations Density 6.145%

    No Known Activations