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. 45564
    Prev
    Next
    INDEX
    Explanations

    references to palm-related imagery or activities, such as palm prints, palm leaves, palm grip, and more

    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
    285
    +0.20
    0.8%
    447
    +0.17
    0.7%
    456
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.20
    0.28
    285
    +0.17
    0.06
    399
    +0.13
    0.07
    Negative Logits
    xual
    -1.02
    OOL
    -0.97
    igslist
    -0.83
     mater
    -0.80
    swick
    -0.79
    rss
    -0.79
    Sov
    -0.78
    ais
    -0.78
    yrinth
    -0.78
    anson
    -0.78
    POSITIVE LOGITS
    print
    1.10
    istry
    0.94
    estamp
    0.92
    printed
    0.90
    prints
    0.89
     fingers
    0.85
     swipe
    0.84
    pad
    0.83
     gesture
    0.83
    uckles
    0.81
    Activations Density 12.761%

    No Known Activations