© 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
    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. 11486
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or steps in a procedure

    oai_token-act-pair · gpt-3.5-turbo

    attributions of importance or significance to statements or facts

    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
    luaj
    -0.78
    cookie
    -0.65
    chev
    -0.65
    abal
    -0.64
    avin
    -0.62
    waukee
    -0.61
    elve
    -0.61
    tight
    -0.60
    opez
    -0.59
    flake
    -0.58
    POSITIVE LOGITS
     done
    1.02
     accomplished
    1.01
     achieved
    0.98
     contrasted
    0.98
     followed
    0.92
     because
    0.89
     supplemented
    0.89
     why
    0.87
     accompanied
    0.87
     untrue
    0.86
    Activations Density 0.134%

    No Known Activations