© 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. 1045
    Prev
    Next
    INDEX
    Explanations

    the word "Sto" combined with specific other suffixes or prefixes

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific venue or location

    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
    URI
    -0.78
    MAL
    -0.76
    bid
    -0.76
    intosh
    -0.70
    EGIN
    -0.69
    é¾įåĸļ士
    -0.69
     GOODMAN
    -0.68
    ITNESS
    -0.68
    LESS
    -0.67
     Pathfinder
    -0.66
    POSITIVE LOGITS
    pped
    0.95
     Sto
    0.91
    pping
    0.91
    ving
    0.82
    ved
    0.78
    pling
    0.73
    zon
    0.73
    pper
    0.73
    agh
    0.72
    igm
    0.71
    Activations Density 0.009%

    No Known Activations