© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20761
    Prev
    Next
    INDEX
    Explanations

    proper nouns or technical terms

    oai_token-act-pair · gpt-3.5-turbo

    references to popular culture and notable figures

    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
    KEY
    -0.70
    APS
    -0.70
    plays
    -0.66
    skill
    -0.66
    ONEY
    -0.66
    Nap
    -0.65
    risk
    -0.64
    pak
    -0.64
    PIN
    -0.63
    wake
    -0.63
    POSITIVE LOGITS
    llor
    0.99
    terday
    0.83
    tenance
    0.82
    ificate
    0.81
    riors
    0.80
    acters
    0.79
    osterone
    0.78
    etheless
    0.77
    theless
    0.75
     hybrids
    0.74
    Activations Density 0.371%

    No Known Activations