© 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. 6723
    Prev
    Next
    INDEX
    Explanations

    references to computer mice and their functionalities

    oai_token-act-pair · gpt-3.5-turbo

    references to mice and mouse actions

    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
    inia
    -0.72
    esson
    -0.72
    rating
    -0.68
    namese
    -0.66
    inyl
    -0.66
    umbing
    -0.65
    isu
    -0.65
    orian
    -0.65
    heit
    -0.64
    aya
    -0.63
    POSITIVE LOGITS
     cursor
    1.12
     pointer
    1.07
    pad
    0.97
    wheel
    0.94
    cules
    0.86
     Mouse
    0.83
    achine
    0.79
    pox
    0.79
     clicks
    0.79
     mouse
    0.77
    Activations Density 0.030%

    No Known Activations