© 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. 18719
    Prev
    Next
    INDEX
    Explanations

    legal or political news and actions

    oai_token-act-pair · gpt-3.5-turbo

    legal terminology and references to judicial actions

    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
    âĹ¼
    -0.74
    _.
    -0.72
    ãĢĤ
    -0.68
    */
    -0.67
     :=
    -0.66
    ItemThumbnailImage
    -0.65
    /?
    -0.65
     etc
    -0.65
    mentioned
    -0.64
    .}
    -0.64
    POSITIVE LOGITS
     Donald
    0.85
     embattled
    0.84
     controversial
    0.79
     presumptive
    0.76
     decriminal
    0.72
     declass
    0.72
     transgender
    0.71
     cryptocurrency
    0.70
     cybersecurity
    0.68
     bitcoin
    0.67
    Activations Density 0.539%

    No Known Activations