Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 3849
    Prev
    Next
    INDEX
    Explanations

    words related to mechanical objects and concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mechanical engineering or robotics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ique
    -0.66
     recogn
    -0.66
    numbered
    -0.63
    WAYS
    -0.63
     cris
    -0.63
     wound
    -0.62
    idine
    -0.61
    id
    -0.61
     centres
    -0.61
     Chow
    -0.60
    POSITIVE LOGITS
     Mechanical
    0.92
    enhagen
    0.80
    ply
    0.77
    taking
    0.74
    lopp
    0.71
    racuse
    0.71
    ansk
    0.70
    perature
    0.69
    partial
    0.69
    party
    0.68
    Activations Density 0.000%

    No Known Activations