© 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. 7-RES-JB
    11. 13369
    Prev
    Next
    INDEX
    Explanations

    the number zero with high relevance

    oai_token-act-pair · gpt-3.5-turbo

    references to "zero" and its implications in various contexts, particularly related to ratings or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.81
    akov
    -0.74
    rough
    -0.74
    lov
    -0.74
    ammad
    -0.74
    areth
    -0.72
    RAW
    -0.69
    TOR
    -0.67
    icken
    -0.65
    Interstitial
    -0.65
    POSITIVE LOGITS
     tolerance
    0.86
     percent
    0.84
     amount
    0.82
     Hedge
    0.81
    xious
    0.75
    MQ
    0.74
     Escape
    0.72
    izes
    0.72
    een
    0.72
    ishly
    0.72
    Activations Density 0.019%

    No Known Activations