© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 24073
    Prev
    Next
    INDEX
    Explanations

    words related to the action of sneezing

    oai_token-act-pair · gpt-3.5-turbo

    words associated with stealthy or sneaky actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĩ
    -0.77
    imon
    -0.73
    falls
    -0.70
    NPR
    -0.70
    imately
    -0.67
    FORM
    -0.65
    Fed
    -0.65
    ento
    -0.63
    minus
    -0.61
     whales
    -0.61
    POSITIVE LOGITS
     Villa
    0.92
    ez
    0.91
    eers
    0.86
    ering
    0.84
    ety
    0.83
    er
    0.83
    ey
    0.82
    aked
    0.80
    aky
    0.79
    eting
    0.77
    Activations Density 0.044%

    No Known Activations