© 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. 2-RES-JB
    11. 20932
    Prev
    Next
    INDEX
    Explanations

    references to the word 'chocolate'

    oai_token-act-pair · gpt-3.5-turbo

    references to chocolate and its effects or associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atives
    -0.79
    WARD
    -0.74
    alez
    -0.73
     Fargo
    -0.70
    baugh
    -0.66
    ATIVE
    -0.66
    href
    -0.66
    SI
    -0.65
     plur
    -0.64
    onent
    -0.63
    POSITIVE LOGITS
     chocolate
    1.02
     cake
    0.93
     pudding
    0.90
    ocolate
    0.88
     cocoa
    0.87
    anut
    0.86
    mint
    0.82
     biscuits
    0.81
     Chocolate
    0.80
     bisc
    0.76
    Activations Density 0.010%

    No Known Activations