© 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. 6-RES-JB
    11. 18507
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Attentenborough"

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the prefix "Att" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thirds
    -0.69
    theless
    -0.62
     euth
    -0.60
     Christensen
    -0.59
     paved
    -0.58
     Vert
    -0.58
     inconven
    -0.58
     Pont
    -0.58
     foss
    -0.57
     sshd
    -0.57
    POSITIVE LOGITS
    urai
    0.89
    achment
    0.86
    ibo
    0.80
    urated
    0.75
    bender
    0.75
    edo
    0.75
    enza
    0.74
    ILA
    0.74
    gee
    0.73
    ments
    0.70
    Activations Density 0.130%

    No Known Activations