© 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. 10087
    Prev
    Next
    INDEX
    Explanations

    disclaimers and legal statements within text

    oai_token-act-pair · gpt-3.5-turbo

    statements asserting non-affiliation or disclaimers regarding content ownership

    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
     dracon
    -0.69
     mirac
    -0.68
    miah
    -0.67
     buried
    -0.67
     catapult
    -0.66
    lined
    -0.66
    itage
    -0.65
     estab
    -0.65
     crunch
    -0.64
     acute
    -0.64
    POSITIVE LOGITS
     Please
    1.61
     Therefore
    1.41
     PLEASE
    1.36
     Feel
    1.28
     Any
    1.28
     Unless
    1.25
     However
    1.24
     Occasionally
    1.24
     Regardless
    1.23
     Accordingly
    1.22
    Activations Density 0.311%

    No Known Activations