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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 880
    Prev
    Next
    INDEX
    Explanations

    baking instructions or recipes

    oai_token-act-pair · gpt-3.5-turbo

    cooking-related terms and actions

    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
    ".[
    -0.34
    )."
    -0.33
    ).[
    -0.33
    ]."
    -0.32
    ."[
    -0.30
    ]).
    -0.29
     subord
    -0.27
    ").
    -0.27
    .).
    -0.26
     ."
    -0.26
    POSITIVE LOGITS
    esides
    0.27
    pard
    0.26
     Canaver
    0.25
    verend
    0.23
    phal
    0.23
    UF
    0.23
    urable
    0.23
     Rebirth
    0.22
    ukong
    0.22
    recated
    0.21
    Activations Density 5.663%

    No Known Activations