© 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. 8-RES-JB
    11. 1330
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of entities such as organizations or people

    oai_token-act-pair · gpt-3.5-turbo

    lists or series of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiName
    -0.70
    ":"/
    -0.64
    ._
    -0.63
    ady
    -0.58
    apper
    -0.56
     Reported
    -0.55
    STER
    -0.55
    ight
    -0.53
    İ
    -0.53
    Below
    -0.53
    POSITIVE LOGITS
     etc
    1.54
    etc
    1.42
     ect
    0.87
     and
    0.84
    whatever
    0.80
     &
    0.73
    and
    0.72
     et
    0.70
     or
    0.64
    ĪĴ
    0.62
    Activations Density 0.258%

    No Known Activations