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. 4-RES-JB
    6. 8824
    Prev
    Next
    INDEX
    Explanations

    mentions of dead animal bodies or carcasses

    oai_token-act-pair · gpt-3.5-turbo

    words associated with animal remains and the context surrounding them

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

    No Comments

    Negative Logits
    uyomi
    -0.88
     Bubble
    -0.72
    dash
    -0.68
    Downloadha
    -0.65
    eer
    -0.65
     Ukrain
    -0.63
    lly
    -0.63
    nels
    -0.63
     PowerPoint
    -0.62
     Tale
    -0.60
    POSITIVE LOGITS
    orns
    1.03
    rast
    0.93
    IJ
    0.91
    orses
    0.91
    acia
    0.90
    azes
    0.86
    atch
    0.86
    ¨
    0.86
    «
    0.84
    orn
    0.84
    Activations Density 0.029%

    No Known Activations