© 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. 3-RES-JB
    11. 15176
    Prev
    Next
    INDEX
    Explanations

    references to a specific entity named "Stone" at different significance levels

    oai_token-act-pair · gpt-3.5-turbo

    the word "Stone" in various contexts

    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
    olulu
    -0.86
    merce
    -0.83
    oresc
    -0.81
    ornia
    -0.79
    uates
    -0.77
    ITAL
    -0.76
    ersive
    -0.75
    orescence
    -0.73
    unct
    -0.72
    unal
    -0.71
    POSITIVE LOGITS
    hill
    0.99
    Stone
    0.92
    works
    0.90
     Stone
    0.89
    falls
    0.89
    breaker
    0.88
    hook
    0.87
    fish
    0.86
    house
    0.85
    bilt
    0.84
    Activations Density 0.006%

    No Known Activations