© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 1064
    Prev
    Next
    INDEX
    Explanations

    words related to projects, programs, and initiatives

    oai_token-act-pair · gpt-3.5-turbo

    nouns and terms associated with specific subjects or themes

    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
    •single token firings
    fires strongly on individual group words: " coalition", " campaign", " squad", " committee", " conference"

    No Comments

    Negative Logits
     prest
    -0.68
     Incarn
    -0.63
     Blossom
    -0.63
     Seym
    -0.58
     Gaw
    -0.58
     Cathedral
    -0.54
     Jagu
    -0.54
     Azerb
    -0.53
    erenn
    -0.53
     Siber
    -0.53
    POSITIVE LOGITS
    lement
    0.57
     ]
    0.57
    resses
    0.56
     ][
    0.56
    ixtape
    0.56
    orts
    0.56
    coins
    0.56
    isms
    0.56
     href
    0.56
    lishes
    0.56
    Activations Density 0.214%

    No Known Activations