© 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. 4-RES-JB
    11. 15205
    Prev
    Next
    INDEX
    Explanations

    instances of the title "Sir" followed by a name in a text

    oai_token-act-pair · gpt-3.5-turbo

    titles or references to individuals who hold the title "Sir"

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

    No Comments

    Negative Logits
     largeDownload
    -0.76
    PRESS
    -0.75
    VB
    -0.71
    ersion
    -0.69
    ktop
    -0.68
     Luxem
    -0.67
    anwhile
    -0.67
    SHIP
    -0.66
    ylon
    -0.66
     pods
    -0.65
    POSITIVE LOGITS
    Sir
    0.88
     Sir
    0.81
    rah
    0.78
    leaf
    0.78
    anas
    0.77
     Hussein
    0.73
    ford
    0.71
     Arthur
    0.70
    cliffe
    0.70
     endors
    0.69
    Activations Density 0.012%

    No Known Activations