© 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. 15462
    Prev
    Next
    INDEX
    Explanations

    proper nouns and locations

    oai_token-act-pair · gpt-3.5-turbo

    variations of the suffix '-ev' or similar endings in words

    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
    ngth
    -0.69
    TRY
    -0.63
     Heard
    -0.62
     Pwr
    -0.61
     Amnesty
    -0.60
     Danger
    -0.57
     MacArthur
    -0.57
    catentry
    -0.56
     words
    -0.56
    ports
    -0.55
    POSITIVE LOGITS
    irus
    1.19
    irtual
    1.08
    ille
    1.01
    ideos
    0.99
    iral
    0.99
    ideo
    0.99
    enture
    0.97
    ski
    0.96
    oice
    0.94
    incial
    0.94
    Activations Density 0.070%

    No Known Activations