© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5555
    Prev
    Next
    INDEX
    Explanations

    commands related to the path or execution of scripts or programs

    oai_token-act-pair · gpt-3.5-turbo

    references to continuous integration (CI) systems and related file paths in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sburg
    -0.81
    sie
    -0.65
    ricting
    -0.64
    eting
    -0.62
    gom
    -0.61
    worms
    -0.60
     Adidas
    -0.60
    oshop
    -0.59
    rab
    -0.59
     Asus
    -0.59
    POSITIVE LOGITS
    itta
    0.74
    001
    0.72
    20439
    0.68
    ~~~~
    0.68
    ANCE
    0.66
    vier
    0.65
    uality
    0.65
    ctr
    0.65
    clave
    0.64
    ocular
    0.64
    Activations Density 0.037%

    No Known Activations