© 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. 17208
    Prev
    Next
    INDEX
    Explanations

    adjectives describing a level or degree of something.

    oai_token-act-pair · gpt-3.5-turbo

    the term "enough" and its variations used in various contexts

    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
     Gh
    -0.68
    bull
    -0.67
     Mens
    -0.64
     Guth
    -0.64
    kind
    -0.63
    raine
    -0.59
    tell
    -0.59
    misc
    -0.59
    cham
    -0.58
    hov
    -0.58
    POSITIVE LOGITS
    hots
    0.71
    ITIES
    0.65
     to
    0.62
    quartered
    0.62
    Ĥİ
    0.59
     quantities
    0.59
     indeed
    0.58
    rehend
    0.58
     visually
    0.56
     intellectually
    0.56
    Activations Density 0.030%

    No Known Activations