© 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. 7677
    Prev
    Next
    INDEX
    Explanations

    terms related to specific organizations or political movements, particularly with the presence of the term "Rac" and "Vacc"

    oai_token-act-pair · gpt-3.5-turbo

    references to political affiliations and notable individuals

    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
    terday
    -0.88
    代
    -0.82
    ι
    -0.71
    使
    -0.70
    FORE
    -0.69
    èĢħ
    -0.63
     Eur
    -0.63
     Gemini
    -0.62
    gian
    -0.62
    addafi
    -0.61
    POSITIVE LOGITS
     Rac
    0.94
    jug
    0.87
    nih
    0.76
    Aren
    0.74
    aido
    0.73
    immune
    0.73
    epend
    0.72
    Pri
    0.72
    egu
    0.72
    qv
    0.71
    Activations Density 0.017%

    No Known Activations