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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 20883
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically those related to individuals named Mohammad

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals named Mohammad

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ific
    -0.79
    bell
    -0.74
     Unch
    -0.71
    iculty
    -0.70
     Cosponsors
    -0.69
    pire
    -0.69
    reated
    -0.68
    illion
    -0.67
    ificent
    -0.67
    illard
    -0.67
    POSITIVE LOGITS
    Û
    1.02
    ammad
    0.81
     Afgh
    0.78
    lihood
    0.75
     versa
    0.75
    ysis
    0.74
    renheit
    0.73
    pour
    0.72
     Imran
    0.71
    ydia
    0.71
    Activations Density 0.018%

    No Known Activations