© 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. 8-RES-JB
    11. 3833
    Prev
    Next
    INDEX
    Explanations

    phrases related to ages specified with a hyphen

    oai_token-act-pair · gpt-3.5-turbo

    references to ages associated with individuals in various contexts, particularly legal or criminal situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owe
    -0.65
     Warfare
    -0.63
     monopoly
    -0.61
     hegemony
    -0.60
     [/
    -0.59
     conventions
    -0.59
    £ı
    -0.59
    lance
    -0.58
    peak
    -0.57
     handshake
    -0.56
    POSITIVE LOGITS
    th
    0.91
    acious
    0.90
     Minutes
    0.88
    %-
    0.80
    teen
    0.77
     unnamed
    0.76
     siblings
    0.76
     cents
    0.75
    ½
    0.75
    yo
    0.74
    Activations Density 0.197%

    No Known Activations