© 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. 4448
    Prev
    Next
    INDEX
    Explanations

    mentions of food items or metaphors related to slicing things

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "slice" and its variations

    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
    founded
    -0.67
    Found
    -0.65
    ities
    -0.65
    administ
    -0.62
     Nich
    -0.62
    development
    -0.61
    quickShipAvailable
    -0.61
    cause
    -0.61
    found
    -0.59
    answered
    -0.59
    POSITIVE LOGITS
     slices
    1.31
     slice
    1.22
    slice
    0.98
     slic
    0.91
    iewicz
    0.88
     slicing
    0.84
    mble
    0.84
     sliced
    0.83
    azo
    0.83
    anut
    0.81
    Activations Density 0.010%

    No Known Activations