© 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. 11-RES-JB
    11. 7796
    Prev
    Next
    INDEX
    Explanations

    specific instances and sources of information mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to sources and related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    needed
    -0.79
    CHECK
    -0.61
    ãģį
    -0.60
    perty
    -0.59
    acerb
    -0.59
    ancial
    -0.59
    xiety
    -0.57
     sizeof
    -0.57
    atism
    -0.55
    oat
    -0.54
    POSITIVE LOGITS
     standpoint
    1.78
     onwards
    1.67
     vantage
    1.59
     perspective
    1.45
     onward
    1.30
     sources
    1.30
     viewpoint
    1.10
     perspectives
    1.07
     source
    1.03
     archives
    1.01
    Activations Density 0.591%

    No Known Activations