© 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. 13020
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific product or company

    oai_token-act-pair · gpt-3.5-turbo

    references to products

    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
    wa
    -0.74
     Surv
    -0.68
    gaard
    -0.65
    stood
    -0.65
     Faul
    -0.63
     SPL
    -0.62
     Fallen
    -0.61
     Declaration
    -0.61
    BUG
    -0.61
     Anders
    -0.60
    POSITIVE LOGITS
    izza
    0.86
    zzle
    0.78
    Downloadha
    0.75
     impart
    0.74
    odge
    0.74
    zz
    0.73
     tremend
    0.69
    agnetic
    0.68
    ggles
    0.67
    afort
    0.66
    Activations Density 0.000%

    No Known Activations