© 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. 9664
    Prev
    Next
    INDEX
    Explanations

    examples of places or situations where someone is living or where events are unfolding

    oai_token-act-pair · gpt-3.5-turbo

    locations or contexts related to living conditions

    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
    vous
    -0.97
    IJ
    -0.80
    hitting
    -0.80
    Applic
    -0.79
    Ħ¢
    -0.74
    ilver
    -0.72
    EY
    -0.70
    asking
    -0.67
    Publisher
    -0.66
    jee
    -0.65
    POSITIVE LOGITS
    agos
    0.77
    abama
    0.74
     Eagle
    0.67
     expectancy
    0.66
     comfortably
    0.65
    oland
    0.63
    ominium
    0.63
     fumes
    0.62
    agles
    0.61
    anwhile
    0.61
    Activations Density 0.125%

    No Known Activations