© 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. 8-RES-JB
    11. 6481
    Prev
    Next
    INDEX
    Explanations

    words related to computer mice

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "mouse" along with related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    namese
    -0.82
    rating
    -0.82
    rators
    -0.77
    orian
    -0.76
    ivals
    -0.76
     Buffy
    -0.73
    inyl
    -0.73
    ivism
    -0.73
    rates
    -0.72
    ieves
    -0.70
    POSITIVE LOGITS
     cursor
    1.09
     pointer
    1.00
    pad
    0.95
    wheel
    0.84
    pox
    0.83
     Mouse
    0.82
    cules
    0.78
    flies
    0.76
     mouse
    0.76
    lette
    0.75
    Activations Density 0.036%

    No Known Activations