© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 21277
    Prev
    Next
    INDEX
    Explanations

    words related to chocolate

    oai_token-act-pair · gpt-3.5-turbo

    references to chocolate in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WARD
    -0.74
    kus
    -0.73
    atives
    -0.72
    inen
    -0.71
     plur
    -0.71
    umbnail
    -0.71
     Imran
    -0.70
    ©¶æ
    -0.70
    SI
    -0.70
    ership
    -0.70
    POSITIVE LOGITS
     pudding
    0.99
     cake
    0.95
    anut
    0.94
     chocolate
    0.93
     biscuits
    0.87
     coated
    0.85
     chip
    0.85
    ocolate
    0.85
     syrup
    0.84
     butter
    0.83
    Activations Density 0.021%

    No Known Activations