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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-RES-JB
    6. 19173
    Prev
    Next
    INDEX
    Explanations

    verbs related to physical actions involving force or effort

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the verb "pull" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    merce
    -0.74
    voy
    -0.73
    ibel
    -0.73
    esa
    -0.72
    icol
    -0.72
    mint
    -0.67
    orld
    -0.67
    SPONSORED
    -0.66
    nown
    -0.66
     Scotia
    -0.65
    POSITIVE LOGITS
     levers
    1.02
     aggro
    0.89
     weeds
    0.86
     away
    0.85
     punches
    0.84
    pull
    0.84
     awa
    0.82
    awed
    0.81
    chairs
    0.81
     off
    0.81
    Activations Density 0.037%

    No Known Activations