© 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. 0-RES-JB
    11. 402
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lack of preference, choice, or restriction

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "any."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    azon
    -0.67
    haw
    -0.62
    Balt
    -0.56
     proverb
    -0.55
    WIND
    -0.53
    GW
    -0.53
    raq
    -0.53
    idad
    -0.52
     largeDownload
    -0.51
     culminating
    -0.51
    POSITIVE LOGITS
     any
    2.83
     ANY
    2.22
     anything
    2.11
     anybody
    1.99
     anyone
    1.98
    any
    1.84
     anytime
    1.80
    Any
    1.78
     Any
    1.75
    anything
    1.73
    Activations Density 0.063%

    No Known Activations