© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 10330
    Prev
    Next
    INDEX
    Explanations

    significant keywords or phrases related to evaluation and assessment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sources
    -0.75
     Accounts
    -0.70
    Links
    -0.64
    NP
    -0.64
    arts
    -0.63
    Enjoy
    -0.63
     aliases
    -0.63
    Rex
    -0.62
    daq
    -0.60
    guards
    -0.60
    POSITIVE LOGITS
     particular
    1.44
     certain
    1.22
     given
    1.12
     specific
    1.08
    uras
    1.06
     person
    1.05
     bunch
    1.02
     piece
    0.99
    rouse
    0.96
     lot
    0.94
    Activations Density 0.316%

    No Known Activations