© 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. 18783
    Prev
    Next
    INDEX
    Explanations

    words related to legal or criminal actions in a law enforcement context

    oai_token-act-pair · gpt-3.5-turbo

    instances of comma usage in text

    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
    ãĤ¦ãĤ¹
    -0.83
    ãģł
    -0.81
    د
    -0.74
    ===
    -0.74
    ificate
    -0.74
    ¶ħ
    -0.73
    ãĥ¯ãĥ³
    -0.72
    etheless
    -0.72
    chnology
    -0.71
    ¥
    -0.70
    POSITIVE LOGITS
     according
    1.40
     spokeswoman
    1.21
     said
    1.14
     officials
    1.12
     spokesman
    1.08
    according
    0.98
     authorities
    0.90
     prosecutors
    0.88
     Superintendent
    0.85
     Assistant
    0.84
    Activations Density 0.282%

    No Known Activations