© 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. 3-RES-JB
    6. 7009
    Prev
    Next
    INDEX
    Explanations

    phrase or words related to chocolate

    oai_token-act-pair · gpt-3.5-turbo

    references to chocolate

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atives
    -0.81
    umbnail
    -0.71
    href
    -0.71
    WARD
    -0.69
    ITNESS
    -0.67
     Fargo
    -0.66
     plur
    -0.66
    baugh
    -0.66
    UCT
    -0.65
    ATIVE
    -0.65
    POSITIVE LOGITS
     chocolate
    0.98
     cake
    0.98
     pudding
    0.92
    ocolate
    0.86
     cocoa
    0.85
    anut
    0.84
    mint
    0.84
     biscuits
    0.83
     flavored
    0.81
     bisc
    0.80
    Activations Density 0.010%

    No Known Activations