© 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. 10-RES-JB
    11. 2760
    Prev
    Next
    INDEX
    Explanations

    words related to snakes

    oai_token-act-pair · gpt-3.5-turbo

    references to snakes and snake-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estine
    -0.79
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.69
    ICAN
    -0.68
    sts
    -0.66
    ãĥĩ
    -0.65
     unification
    -0.65
    Ħ¢
    -0.65
    rica
    -0.65
    ãĥ¬
    -0.63
    vre
    -0.63
    POSITIVE LOGITS
    bite
    1.18
     venom
    0.97
     snakes
    0.92
    hook
    0.84
    pit
    0.83
    tail
    0.83
     snake
    0.83
    lings
    0.82
    Snake
    0.81
     bite
    0.81
    Activations Density 0.043%

    No Known Activations