© 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. 20229
    Prev
    Next
    INDEX
    Explanations

    terms related to radical ideologies or movements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to radical ideologies or actions

    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
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.75
    FACE
    -0.75
    veyard
    -0.73
    fman
    -0.72
    ursed
    -0.72
    ords
    -0.71
    ORD
    -0.68
    BLE
    -0.67
    aird
    -0.67
    hner
    -0.66
    POSITIVE LOGITS
    ization
    1.28
    ism
    1.23
     Islamists
    1.20
    isation
    1.19
     Islamist
    1.16
    izing
    1.15
    ized
    1.15
    ising
    1.08
     leftist
    1.04
     Islamic
    1.02
    Activations Density 0.037%

    No Known Activations