© 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. 2614
    Prev
    Next
    INDEX
    Explanations

    mentions of primate species, specifically great apes like chimpanzees and gorillas

    oai_token-act-pair · gpt-3.5-turbo

    references to different species of primates, particularly great apes

    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
    HUD
    -0.80
    sol
    -0.74
    oppable
    -0.74
    gren
    -0.71
    bringer
    -0.70
    spr
    -0.67
     Seym
    -0.67
    bg
    -0.66
    ved
    -0.66
    EA
    -0.65
    POSITIVE LOGITS
    zee
    1.14
    zees
    1.14
     chimpanzees
    1.12
     apes
    1.00
     chimpan
    0.94
     primates
    0.91
     gorilla
    0.89
     Haram
    0.87
     saf
    0.77
    utan
    0.77
    Activations Density 0.037%

    No Known Activations