© 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. 8-RES-JB
    11. 6961
    Prev
    Next
    INDEX
    Explanations

    information about people's work history

    oai_token-act-pair · gpt-3.5-turbo

    employment-related phrases

    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
    BACK
    -0.71
    BR
    -0.67
    heim
    -0.66
    é¾
    -0.66
    edition
    -0.63
    pour
    -0.63
    909
    -0.62
    accompan
    -0.62
    ν
    -0.62
    ι
    -0.62
    POSITIVE LOGITS
    geries
    0.83
     awhile
    0.79
    abit
    0.79
     hire
    0.79
    bidden
    0.79
     him
    0.78
    gotten
    0.74
     instance
    0.74
     them
    0.73
     somebody
    0.72
    Activations Density 0.110%

    No Known Activations