© 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. 17100
    Prev
    Next
    INDEX
    Explanations

    words indicating high degree or level of something

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that express varying degrees of intensity or quality

    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
    agents
    -0.81
    adan
    -0.79
    */(
    -0.74
     Crimes
    -0.71
     Flavoring
    -0.71
    icago
    -0.71
    ngth
    -0.70
    assador
    -0.69
    issance
    -0.68
    dos
    -0.66
    POSITIVE LOGITS
     skewed
    1.11
     variable
    1.03
     erratic
    0.98
     varied
    0.98
     fragmented
    0.97
     limited
    0.97
     uneven
    0.96
     muted
    0.94
     murky
    0.94
     sparse
    0.91
    Activations Density 0.161%

    No Known Activations