Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 14803
    Prev
    Next
    INDEX
    Explanations

    keyboard shortcuts related to software operations

    oai_token-act-pair · gpt-3.5-turbo

    keyboard shortcuts and input commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vier
    -0.73
    fund
    -0.72
    sale
    -0.69
     Bridgewater
    -0.68
    angel
    -0.66
     pension
    -0.65
    olina
    -0.65
    fam
    -0.65
     Loan
    -0.64
     burial
    -0.64
    POSITIVE LOGITS
     buttons
    1.33
     joystick
    1.25
     button
    1.15
     CTRL
    1.04
     Ctrl
    1.04
     keyboard
    1.03
     shortcut
    1.03
    trl
    1.03
     cursor
    1.03
     levers
    1.02
    Activations Density 0.165%

    No Known Activations