© 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. 11-RES-JB
    11. 17214
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something is not as it appears or is more complex than initially thought

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing comparisons or contrasts in situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ward
    -0.72
     Galile
    -0.65
    eria
    -0.63
    etts
    -0.59
     +/-
    -0.59
     Dane
    -0.58
     Kah
    -0.58
    gard
    -0.58
    cean
    -0.58
     miscarriage
    -0.58
    POSITIVE LOGITS
     sounds
    0.94
     sounded
    0.83
     appears
    0.83
     looks
    0.80
     Seems
    0.78
     Appears
    0.77
     appeared
    0.76
     appear
    0.76
     looked
    0.74
     seems
    0.73
    Activations Density 0.061%

    No Known Activations