© 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. 10-RES-JB
    11. 10221
    Prev
    Next
    INDEX
    Explanations

    mentions of government agencies and officials

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations or departments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gyn
    -0.65
    girl
    -0.64
    lehem
    -0.64
    pour
    -0.63
    oké
    -0.60
     Scores
    -0.59
    etry
    -0.58
     couples
    -0.58
     divor
    -0.58
     lad
    -0.58
    POSITIVE LOGITS
     own
    0.97
     Office
    0.92
     flagship
    0.91
     inability
    0.89
     newest
    0.88
     deliberations
    0.86
     mandate
    0.81
     insistence
    0.80
     largest
    0.79
     decision
    0.79
    Activations Density 0.139%

    No Known Activations