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. 7-RES-JB
    6. 23177
    Prev
    Next
    INDEX
    Explanations

    commands or instructions

    oai_token-act-pair · gpt-3.5-turbo

    urgent advisory statements or warnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cre
    -0.53
    sylv
    -0.52
    sis
    -0.51
    iferation
    -0.51
    feld
    -0.51
    schild
    -0.51
    ô
    -0.49
    click
    -0.48
    Tonight
    -0.48
    iew
    -0.48
    POSITIVE LOGITS
    cellaneous
    0.61
    ":""},{"
    0.54
    !:
    0.54
    merce
    0.53
     Amph
    0.49
    zbollah
    0.49
    *:
    0.49
     MFT
    0.48
    BILITIES
    0.48
    drm
    0.48
    Activations Density 1.345%

    No Known Activations