© 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. 1-RES-JB
    11. 16886
    Prev
    Next
    INDEX
    Explanations

    mentions of political ideologies, specifically fascism

    oai_token-act-pair · gpt-3.5-turbo

    references to fascism and related ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tis
    -0.99
    LOAD
    -0.80
    20439
    -0.79
    bits
    -0.78
    teen
    -0.78
    monds
    -0.73
    PT
    -0.72
    Bridge
    -0.72
    ALE
    -0.71
    BY
    -0.69
    POSITIVE LOGITS
     fascists
    1.25
     fascist
    1.19
     fascism
    1.19
    olini
    1.13
    ascist
    1.03
     dictatorship
    1.03
     dictator
    1.00
     salute
    0.97
     Fasc
    0.93
    emetery
    0.87
    Activations Density 0.010%

    No Known Activations