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

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 4968
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "South Africa" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to South Africa and its related socio-political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hower
    -0.63
     favor
    -0.61
     variance
    -0.61
     casc
    -0.60
    processing
    -0.59
     sparse
    -0.56
     hump
    -0.56
    Large
    -0.55
    letcher
    -0.55
    lehem
    -0.53
    POSITIVE LOGITS
    istan
    0.90
    amaru
    0.75
    atchewan
    0.75
     Zealand
    0.74
    arde
    0.72
    upid
    0.72
    atoon
    0.72
    ombat
    0.70
    Ú
    0.70
     Polic
    0.69
    Activations Density 0.042%

    No Known Activations