© 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. 1-RES-JB
    11. 13382
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences with the word "attributed" followed by a high activation number

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lake
    -0.74
    lite
    -0.71
    thin
    -0.69
    cre
    -0.67
    astern
    -0.65
    cum
    -0.62
     Fusion
    -0.62
     Stras
    -0.60
    ben
    -0.59
     Sandwich
    -0.59
    POSITIVE LOGITS
     attribut
    1.09
     attributed
    1.01
     corrid
    0.97
     attribution
    0.89
     acknow
    0.87
     unden
    0.83
     blame
    0.83
     misunder
    0.82
    inished
    0.80
     conclud
    0.76
    Activations Density 0.008%

    No Known Activations