© 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. 1925
    Prev
    Next
    INDEX
    Explanations

    organizations and committees related to policy and research

    oai_token-act-pair · gpt-3.5-turbo

    references to various organizations and committees

    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
     alarms
    -0.72
     lif
    -0.70
     scalp
    -0.70
     derivatives
    -0.69
     legend
    -0.68
     razor
    -0.68
     intuition
    -0.68
     heats
    -0.67
     glory
    -0.67
     shine
    -0.67
    POSITIVE LOGITS
     Against
    1.00
     Provision
    0.85
     Of
    0.84
    ozo
    0.82
     of
    0.74
     Strategic
    0.73
    Wars
    0.73
    Sport
    0.73
     Rooms
    0.72
     Projects
    0.72
    Activations Density 0.168%

    No Known Activations