© 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. 10-RES-JB
    11. 24555
    Prev
    Next
    INDEX
    Explanations

    political and societal commentary

    oai_token-act-pair · gpt-3.5-turbo

    arguments related to justice and responsibility in a societal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    [/
    -0.93
    Enlarge
    -0.86
    ãĢį
    -0.86
    \",
    -0.84
    âĸł
    -0.80
    ?ãĢį
    -0.79
    ''
    -0.78
    ãĥ´ãĤ¡
    -0.76
    </
    -0.76
     kinda
    -0.75
    POSITIVE LOGITS
     denounce
    1.04
     condemn
    1.03
     repud
    0.97
     dehuman
    0.96
     nonviolent
    0.95
     complicit
    0.94
     courageous
    0.91
     acquies
    0.90
     complicity
    0.90
     oppressed
    0.90
    Activations Density 1.103%

    No Known Activations