© 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. 10-RES-JB
    6. 9230
    Prev
    Next
    INDEX
    Explanations

    phrases related to government crackdowns and suppression of civil liberties

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to governmental oppression and civil liberties violations

    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
     Hitchcock
    -0.77
    ortality
    -0.77
    intendent
    -0.71
    imum
    -0.71
    Ult
    -0.70
    nard
    -0.70
    HUD
    -0.69
    ondo
    -0.68
    nesia
    -0.67
     Prescott
    -0.67
    POSITIVE LOGITS
     dissent
    1.69
     dissidents
    1.49
     dissenting
    1.37
     whistleblowers
    1.31
     NGOs
    1.27
     minorities
    1.22
     protests
    1.18
     protesters
    1.16
     activists
    1.16
     peaceful
    1.15
    Activations Density 0.318%

    No Known Activations