© 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. 9412
    Prev
    Next
    INDEX
    Explanations

    references related to Fidel Castro

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific influential figures, particularly Fidel Castro

    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
    wagen
    -0.70
    esville
    -0.70
    Reward
    -0.68
    ueller
    -0.68
     resc
    -0.67
    #$
    -0.67
    ween
    -0.66
    FIELD
    -0.66
    raise
    -0.65
    ummer
    -0.65
    POSITIVE LOGITS
     Fidel
    0.94
    inx
    0.92
     Mandarin
    0.76
     Emer
    0.76
     cane
    0.71
    ency
    0.71
    apple
    0.70
    ifix
    0.69
    inant
    0.69
    antly
    0.68
    Activations Density 0.025%

    No Known Activations