© 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. 0-RES-JB
    11. 8304
    Prev
    Next
    INDEX
    Explanations

    references to authoritative or official lists or collections

    oai_token-act-pair · gpt-3.5-turbo

    references to 'canon' or 'canonical' concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kee
    -0.89
    nesota
    -0.73
    usterity
    -0.73
    iveness
    -0.72
    itaire
    -0.72
    Swe
    -0.70
     Afgh
    -0.69
    jit
    -0.68
     bounce
    -0.67
     gamb
    -0.66
    POSITIVE LOGITS
     Canon
    3.66
     canon
    3.36
    canon
    2.62
     canonical
    2.21
     Celest
    1.20
     Nikon
    1.16
     Archbishop
    1.01
     bapt
    1.01
     heresy
    0.96
     Scripture
    0.96
    Activations Density 0.033%

    No Known Activations