© 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. 10-RES-JB
    11. 13692
    Prev
    Next
    INDEX
    Explanations

    mentions of professions, particularly focusing on chefs

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various professions and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Territories
    -0.76
    ilogy
    -0.65
     Virus
    -0.64
    croft
    -0.62
    bush
    -0.62
    lain
    -0.61
    nce
    -0.59
    osure
    -0.58
     Lights
    -0.58
    atever
    -0.58
    POSITIVE LOGITS
    hip
    1.38
    hips
    1.31
    paces
    1.19
    '
    1.15
     who
    1.13
    who
    0.95
    mith
    0.94
     unions
    0.92
     themselves
    0.91
    ']
    0.91
    Activations Density 0.307%

    No Known Activations