© 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. 9-RES-JB
    6. 5274
    Prev
    Next
    INDEX
    Explanations

    proper nouns and place names related to events involving law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals involved in various incidents

    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
    notations
    -0.77
     endorsements
    -0.70
    ivalry
    -0.68
    wcsstore
    -0.66
     revolution
    -0.66
     dominates
    -0.64
     Directors
    -0.63
     championships
    -0.61
     Represent
    -0.61
     shaping
    -0.61
    POSITIVE LOGITS
     unconscious
    0.89
     tresp
    0.84
     unlawfully
    0.82
     peacefully
    0.81
     shortly
    0.79
     detained
    0.77
     suspected
    0.76
     orally
    0.75
     handcuffed
    0.75
     briefly
    0.75
    Activations Density 0.382%

    No Known Activations