© 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. 9-RES-JB
    11. 3434
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical appearance

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods and parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tremend
    -0.82
     challeng
    -0.81
     corrid
    -0.80
     enthusi
    -0.79
    ascus
    -0.79
     activ
    -0.78
     optimizations
    -0.77
     unnecessary
    -0.77
     workaround
    -0.77
     feasible
    -0.77
    POSITIVE LOGITS
     Their
    1.43
     His
    1.32
     They
    1.32
     Its
    1.29
     Together
    1.27
     Born
    1.25
     Married
    1.23
     Unlike
    1.22
     Neither
    1.21
     Each
    1.20
    Activations Density 0.341%

    No Known Activations