© 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. 13955
    Prev
    Next
    INDEX
    Explanations

    statements contrasting different perspectives or qualities

    oai_token-act-pair · gpt-3.5-turbo

    assertions or statements about reality and conditions in various contexts

    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
     ILCS
    -0.68
    ãĥĺ
    -0.63
     favourites
    -0.61
     Uniform
    -0.58
     Eps
    -0.58
     Mile
    -0.57
     unsolved
    -0.57
     unused
    -0.57
     Vand
    -0.57
     favorites
    -0.56
    POSITIVE LOGITS
    Rather
    0.96
    isite
    0.87
    gemony
    0.85
     Rather
    0.81
    actually
    0.79
    rather
    0.78
    're
    0.78
    ÃŃs
    0.77
    inis
    0.72
     actually
    0.72
    Activations Density 0.149%

    No Known Activations