© 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. 0-RES-JB
    11. 1144
    Prev
    Next
    INDEX
    Explanations

    names of people with variations of the name "Lauren" or "Margaret"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Pg
    -0.72
     Kab
    -0.69
    DP
    -0.65
     âĢİ
    -0.65
     Jab
    -0.65
    webkit
    -0.64
    MI
    -0.64
     Punch
    -0.64
    frames
    -0.63
    GM
    -0.63
    POSITIVE LOGITS
    uren
    3.23
    iren
    2.41
    irens
    1.68
    riel
    1.60
    aren
    1.36
    aret
    1.35
    arie
    1.09
     Belle
    0.95
     Haven
    0.90
    entric
    0.88
    Activations Density 0.035%

    No Known Activations