© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3564
    Prev
    Next
    INDEX
    Explanations

    names of individuals or entities, particularly those with a strong presence

    oai_token-act-pair · gpt-3.5-turbo

    references to influential or notable individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     metic
    -0.92
    senal
    -0.87
    ñ
    -0.73
    ò
    -0.73
    nic
    -0.72
    Þ
    -0.69
     tremend
    -0.68
     Mell
    -0.68
    BuyableInstoreAndOnline
    -0.67
     teasp
    -0.66
    POSITIVE LOGITS
    ord
    0.93
    az
    0.84
    ORD
    0.83
    oss
    0.80
    ago
    0.75
    ashi
    0.75
     Jord
    0.74
    aku
    0.73
    ai
    0.71
     Kaz
    0.71
    Activations Density 0.198%

    No Known Activations