© 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. 7199
    Prev
    Next
    INDEX
    Explanations

    descriptions of improvement or enhancement

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to outcomes and consequences

    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
    [/
    -0.77
     (@
    -0.77
     ['
    -0.76
     [/
    -0.74
     [+
    -0.74
    _-
    -0.72
    ](
    -0.70
     ["
    -0.70
    ->
    -0.68
     Explicit
    -0.66
    POSITIVE LOGITS
     extravag
    0.85
     entrepreneurial
    0.82
     unwelcome
    0.79
     fortunes
    0.79
     bustling
    0.78
     lucrative
    0.76
     glamorous
    0.76
     riches
    0.73
     attracting
    0.73
     fearsome
    0.72
    Activations Density 1.083%

    No Known Activations