© 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. 4-RES-JB
    11. 19553
    Prev
    Next
    INDEX
    Explanations

    mentions of "Otters"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Otter" in various contexts

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

    No Comments

    Negative Logits
    âĸ¬
    -0.83
    FUL
    -0.77
    Interested
    -0.71
    Ùħ
    -0.71
    pmwiki
    -0.71
    士
    -0.71
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.71
    ãĤ¼ãĤ¦ãĤ¹
    -0.70
     STEP
    -0.70
    é¾įå¥ij士
    -0.68
    POSITIVE LOGITS
    terness
    1.18
    ago
    1.07
    oscope
    1.06
    ric
    1.04
    olith
    1.01
    itles
    1.01
    omy
    0.97
     Ot
    0.96
    ocol
    0.95
    oken
    0.94
    Activations Density 0.010%

    No Known Activations