© 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. 9-RES-JB
    11. 10060
    Prev
    Next
    INDEX
    Explanations

    objects or abstract concepts related to searching or finding

    oai_token-act-pair · gpt-3.5-turbo

    references to searching for people, places, or things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elvet
    -0.63
     PROG
    -0.62
     Notting
    -0.60
    ħĭ
    -0.60
    ICA
    -0.58
    noon
    -0.57
    amon
    -0.57
    ignt
    -0.56
    xon
    -0.56
     Rico
    -0.56
    POSITIVE LOGITS
     suitable
    1.16
     willing
    0.88
     elusive
    0.83
     worthy
    0.82
     replacements
    0.81
     alternatives
    0.77
     inspiration
    0.77
     suited
    0.75
     trustworthy
    0.74
     replacement
    0.70
    Activations Density 0.360%

    No Known Activations