© 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. 4223
    Prev
    Next
    INDEX
    Explanations

    dates expressed in the format of a two-digit year followed by a two-digit number

    oai_token-act-pair · gpt-3.5-turbo

    instances of the number "20" 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
    plom
    -0.74
    pora
    -0.73
    hei
    -0.71
    afort
    -0.70
    ño
    -0.70
    ablo
    -0.65
    ãĥ£
    -0.64
    osal
    -0.64
    henko
    -0.63
    kell
    -0.62
    POSITIVE LOGITS
    âĸĪâĸĪ
    1.05
    committee
    0.89
    skirts
    0.88
    th
    0.86
    200000
    0.84
    ISH
    0.83
    61
    0.79
    %"
    0.79
    40
    0.78
    isher
    0.78
    Activations Density 0.060%

    No Known Activations