© 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. 10-RES-JB
    11. 14030
    Prev
    Next
    INDEX
    Explanations

    phrases related to complex, challenging, or critical situations

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific situation or condition

    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
    cott
    -0.79
    azines
    -0.77
    cot
    -0.74
    ithe
    -0.73
     Flavoring
    -0.73
    ipedia
    -0.72
    tool
    -0.71
    netic
    -0.68
    rib
    -0.68
    tein
    -0.67
    POSITIVE LOGITS
     unfolding
    1.14
     involving
    0.98
     situation
    0.96
     unfolded
    0.93
     wors
    0.93
     situations
    0.92
     quo
    0.92
     worsened
    0.90
     Situation
    0.88
     confronting
    0.86
    Activations Density 0.046%

    No Known Activations