© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 20519
    Prev
    Next
    INDEX
    Explanations

    words related to eyes or visual perception

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Malt
    -1.19
     malt
    -0.97
     MIN
    -0.89
     Bridgewater
    -0.83
     mono
    -0.82
     Brut
    -0.82
    í
    -0.82
    MIN
    -0.81
     fragment
    -0.80
     Lithuan
    -0.79
    POSITIVE LOGITS
    aw
    1.83
    Aw
    1.42
    AW
    1.42
    haw
    1.41
    aws
    1.40
     Aw
    1.37
    shaw
    1.37
     Shaw
    1.28
    ew
    1.25
     Ow
    1.23
    Activations Density 0.281%

    No Known Activations