Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 15147
    Prev
    Next
    INDEX
    Explanations

    references to medical doctors

    oai_token-act-pair · gpt-3.5-turbo

    titles or designations of medical and authoritative professionals

    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
    TOR
    -0.79
    BAT
    -0.78
     tremend
    -0.76
    THIS
    -0.75
    ixtape
    -0.75
    Interstitial
    -0.75
    TPP
    -0.72
    Sov
    -0.71
     unden
    -0.71
    STATE
    -0.71
    POSITIVE LOGITS
     Mr
    0.83
     Richard
    0.81
     Claus
    0.80
     David
    0.80
     William
    0.79
     Prof
    0.79
     Joseph
    0.78
     Daniel
    0.77
    sson
    0.77
     Andrew
    0.77
    Activations Density 0.092%

    No Known Activations