© 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. 9-RES-JB
    11. 4908
    Prev
    Next
    INDEX
    Explanations

    phrases related to enabling or permitting actions or conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating enabling or facilitative actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    been
    -0.72
    ask
    -0.71
    daq
    -0.69
    ko
    -0.68
    displayText
    -0.66
    lean
    -0.65
    ohm
    -0.63
    kind
    -0.62
    worn
    -0.62
    ãĥĩãĤ£
    -0.61
    POSITIVE LOGITS
     us
    1.21
     them
    0.91
     him
    0.85
    Reviewer
    0.84
     me
    0.83
     researchers
    0.80
     doctors
    0.73
     astronomers
    0.73
     you
    0.73
     ample
    0.73
    Activations Density 0.092%

    No Known Activations