© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 19400
    Prev
    Next
    INDEX
    Explanations

    commands related to navigating through directories and installing packages in coding environments

    oai_token-act-pair · gpt-3.5-turbo

    commands and terms related to software installation and package management in a coding context

    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
    bringer
    -0.73
     Plane
    -0.73
     Principle
    -0.72
    rored
    -0.72
    ELD
    -0.72
    externalActionCode
    -0.71
    )].
    -0.70
    irds
    -0.66
     appealed
    -0.65
     Styles
    -0.65
    POSITIVE LOGITS
     gcc
    0.69
     ./
    0.66
    username
    0.65
     cz
    0.65
    cd
    0.64
     tyr
    0.63
     wiser
    0.63
     blat
    0.62
     sher
    0.62
    itude
    0.62
    Activations Density 0.050%

    No Known Activations