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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9436
    Prev
    Next
    INDEX
    Explanations

    lines of text ending with a certain number

    oai_token-act-pair · gpt-3.5-turbo

    references to specific "line" designations in a document

    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
    CVE
    -0.92
    sylvania
    -0.74
    ndum
    -0.73
    âĺħâĺħ
    -0.72
    CLASSIFIED
    -0.71
     tremend
    -0.68
    ILD
    -0.68
    PDATE
    -0.66
     unden
    -0.66
    ILY
    -0.66
    POSITIVE LOGITS
    backer
    1.22
    aments
    1.17
    ups
    1.11
    ages
    1.04
    breaks
    0.89
    up
    0.87
    breaking
    0.86
    points
    0.79
    breakers
    0.79
    draw
    0.78
    Activations Density 0.062%

    No Known Activations