© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 19000
    Prev
    Next
    INDEX
    Explanations

    phrases related to styles or ways of doing things

    oai_token-act-pair · gpt-3.5-turbo

    structured references to ways of doing things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orters
    -0.68
    addons
    -0.66
    usted
    -0.63
    algia
    -0.63
    verbs
    -0.60
    dar
    -0.59
     oun
    -0.58
    raltar
    -0.58
    umar
    -0.57
     SPD
    -0.57
    POSITIVE LOGITS
     throughout
    0.75
     (<
    0.72
     resembling
    0.70
     thereafter
    0.70
    .
    0.69
     reminiscent
    0.67
     thanks
    0.67
     during
    0.66
    ;
    0.65
     without
    0.65
    Activations Density 0.195%

    No Known Activations