© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 23907
    Prev
    Next
    INDEX
    Explanations

    phrases related to political extremism and specific organizations or movements

    oai_token-act-pair · gpt-3.5-turbo

    references to the alt-right movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     destro
    -0.87
     Pru
    -0.68
    apest
    -0.68
     Ads
    -0.65
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.65
    zeb
    -0.65
     payable
    -0.64
     Bord
    -0.63
     bom
    -0.63
    amaz
    -0.62
    POSITIVE LOGITS
    shock
    0.79
    dial
    0.76
    ography
    0.74
    politics
    0.73
    ographers
    0.72
    Raid
    0.72
    wo
    0.71
    oak
    0.71
    Knight
    0.70
    ionics
    0.70
    Activations Density 0.053%

    No Known Activations