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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 17583
    Prev
    Next
    INDEX
    Explanations

    acts of physical aggression and violence involving specific body parts or physical objects

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of physical actions and their spatial contexts

    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
    assadors
    -0.83
    HCR
    -0.82
    thood
    -0.82
    arians
    -0.81
    arcity
    -0.80
    SPONSORED
    -0.79
    ItemThumbnailImage
    -0.78
    glers
    -0.78
    CLASSIFIED
    -0.76
    cially
    -0.76
    POSITIVE LOGITS
     proverbial
    1.08
     doorway
    1.02
     rooft
    1.01
     closet
    0.98
     unconscious
    0.98
     tube
    0.98
     attic
    0.97
     chest
    0.94
     throats
    0.94
     tubes
    0.94
    Activations Density 0.700%

    No Known Activations