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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7449
    Prev
    Next
    INDEX
    Explanations

    locations or places, specifically the city of Pensacola

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific locations and organizations

    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
    eners
    -0.75
    ELL
    -0.71
    WORK
    -0.70
     Gleaming
    -0.67
     Territories
    -0.65
     WARN
    -0.64
    laughs
    -0.64
    ADS
    -0.63
    Stud
    -0.63
    UGH
    -0.63
    POSITIVE LOGITS
    acle
    0.85
    cipled
    0.79
    ensical
    0.77
    agons
    0.77
    acles
    0.77
    nces
    0.76
    borough
    0.73
    atell
    0.73
    paio
    0.73
    pace
    0.73
    Activations Density 0.020%

    No Known Activations