© 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. 8606
    Prev
    Next
    INDEX
    Explanations

    mentions of specific technology products or software

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific brands or products

    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
    20439
    -0.83
    /-
    -0.69
    soever
    -0.64
    Ô
    -0.62
    Ö
    -0.61
    âĵĺ
    -0.61
     [&
    -0.59
    lain
    -0.58
    flies
    -0.56
     msec
    -0.56
    POSITIVE LOGITS
    senal
    0.66
    ŃĶ
    0.63
    topia
    0.63
     Wire
    0.62
    icide
    0.59
    Vote
    0.58
    HQ
    0.56
     Voting
    0.56
    vote
    0.55
    mobile
    0.55
    Activations Density 0.586%

    No Known Activations