© 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. 0-RES-JB
    11. 13714
    Prev
    Next
    INDEX
    Explanations

    words related to situations of high importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    references to hierarchical structures or levels

    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
     wasteful
    -0.64
     protocol
    -0.63
     whites
    -0.61
     Apollo
    -0.61
     cleaned
    -0.61
     Cooperation
    -0.59
     SPD
    -0.59
     grips
    -0.58
     fee
    -0.57
     REUTERS
    -0.57
    POSITIVE LOGITS
    lev
    4.89
    levard
    1.52
    Lev
    1.46
    lem
    1.42
    lez
    1.30
    leg
    1.23
     lev
    1.08
     Elev
    1.07
    lege
    1.07
    lav
    1.05
    Activations Density 0.012%

    No Known Activations