© 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 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. 19367
    Prev
    Next
    INDEX
    Explanations

    acronyms related to organizations or programs

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms related to organizations or programs

    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
    esville
    -0.75
    enegger
    -0.71
    umar
    -0.61
    panic
    -0.61
    stan
    -0.61
     priv
    -0.60
    shire
    -0.59
    vet
    -0.58
    adem
    -0.57
    quest
    -0.56
    POSITIVE LOGITS
    OPS
    0.98
    AR
    0.92
    IAS
    0.90
    HR
    0.90
    OD
    0.90
    UD
    0.90
    HE
    0.90
    IDS
    0.89
    ASE
    0.89
    °
    0.89
    Activations Density 0.137%

    No Known Activations