© 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. 10-RES-JB
    11. 3375
    Prev
    Next
    INDEX
    Explanations

    references to specific names or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to lists or rankings typically in a prominent format

    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
    Wil
    -1.02
     Bows
    -0.96
    WB
    -0.95
     Webb
    -0.91
    ws
    -0.89
     Woo
    -0.88
    SW
    -0.87
    wi
    -0.87
     Hels
    -0.86
     Wes
    -0.86
    POSITIVE LOGITS
    ent
    0.99
    card
    0.91
    cards
    0.91
    parser
    0.88
    ents
    0.83
    ENT
    0.82
    Gall
    0.82
    ñ
    0.81
    ental
    0.80
    phil
    0.79
    Activations Density 0.407%

    No Known Activations