© 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. 7-RES-JB
    11. 2259
    Prev
    Next
    INDEX
    Explanations

    words related to various procurement activities and processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to processes and procurement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    holders
    -0.94
    men
    -0.85
    irs
    -0.82
    DonaldTrump
    -0.75
     Falk
    -0.75
    holder
    -0.75
    gow
    -0.74
    itsch
    -0.74
    man
    -0.72
    woman
    -0.72
    POSITIVE LOGITS
    rast
    1.53
    ategory
    0.95
    urnal
    0.93
     proc
    0.93
    urrent
    0.93
    stant
    0.89
    ĵĺ
    0.83
     unfocusedRange
    0.77
    rocal
    0.75
    uracy
    0.73
    Activations Density 0.076%

    No Known Activations