© 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. 20393
    Prev
    Next
    INDEX
    Explanations

    acronyms or abbreviations related to technology

    oai_token-act-pair · gpt-3.5-turbo

    acronyms or abbreviations related to specific terms or organizations

    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
    geist
    -0.81
    gerald
    -0.79
    doms
    -0.77
    berg
    -0.76
    enberg
    -0.76
    glers
    -0.75
    omorphic
    -0.74
    ãĥĥ
    -0.74
    lon
    -0.73
    orio
    -0.72
    POSITIVE LOGITS
    IST
    1.31
    ACK
    1.17
    ADE
    1.13
    END
    1.12
    HO
    1.12
    OST
    1.12
    OX
    1.11
    OW
    1.11
    ICE
    1.10
    OSE
    1.09
    Activations Density 0.075%

    No Known Activations