© 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. 2-RES-JB
    11. 23619
    Prev
    Next
    INDEX
    Explanations

    company names or references to corporations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Co" followed by a number

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.69
     IMAGES
    -0.68
     GOODMAN
    -0.67
     Marketable
    -0.66
    selves
    -0.66
    lihood
    -0.63
     Hungarian
    -0.63
     guiActiveUn
    -0.62
    acious
    -0.61
     Subjects
    -0.61
    POSITIVE LOGITS
    venants
    0.96
    ops
    0.95
    asters
    0.93
    op
    0.93
    ingen
    0.93
    Co
    0.92
    operative
    0.91
    aching
    0.90
    oco
    0.89
    aches
    0.87
    Activations Density 0.015%

    No Known Activations