© 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. 13970
    Prev
    Next
    INDEX
    Explanations

    facts or rankings related to the second position

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing rankings or comparisons of size or significance

    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
    Ń·
    -0.67
     formula
    -0.64
     resume
    -0.63
     Noir
    -0.60
     Richards
    -0.59
     Tune
    -0.57
     Robertson
    -0.57
     vapor
    -0.56
     mirrors
    -0.56
    IBLE
    -0.55
    POSITIVE LOGITS
    generation
    1.37
    largest
    1.34
    highest
    1.32
    ranked
    1.29
    tier
    1.27
    degree
    1.26
    ranking
    1.20
    favorite
    1.18
    worst
    1.17
    rate
    1.13
    Activations Density 0.025%

    No Known Activations