© 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. 6-RES-JB
    11. 9908
    Prev
    Next
    INDEX
    Explanations

    words related to keen observation and insight

    oai_token-act-pair · gpt-3.5-turbo

    terms related to astrology, particularly the term "astute."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hyde
    -0.85
    LOAD
    -0.76
    Ô
    -0.76
    essee
    -0.72
    DragonMagazine
    -0.70
    士
    -0.69
     Nightmares
    -0.68
    ppo
    -0.67
    edom
    -0.66
     Commercial
    -0.66
    POSITIVE LOGITS
    rolog
    1.04
    rot
    1.04
    rology
    1.04
    igmat
    1.01
    ro
    1.00
    osc
    0.92
    ral
    0.90
    reet
    0.90
    rog
    0.89
    rob
    0.88
    Activations Density 0.038%

    No Known Activations