© 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. 1-RES-JB
    11. 16340
    Prev
    Next
    INDEX
    Explanations

    commands or actions related to enabling or disabling functions or features

    oai_token-act-pair · gpt-3.5-turbo

    references to disabling or enabling features and functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eal
    -0.85
    alez
    -0.83
    aternity
    -0.79
    rio
    -0.75
    alg
    -0.74
    kaya
    -0.74
    ablishment
    -0.71
    Mart
    -0.70
    eday
    -0.70
    arah
    -0.70
    POSITIVE LOGITS
     disable
    1.27
     disabling
    1.16
    Disable
    0.98
     inhibitor
    0.91
    ments
    0.90
    MENTS
    0.90
     inhibitors
    0.89
     inhibition
    0.88
    disable
    0.84
    MENT
    0.84
    Activations Density 0.018%

    No Known Activations