© 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. 3-RES-JB
    11. 16927
    Prev
    Next
    INDEX
    Explanations

    relationships and connections between people, such as friends and family

    oai_token-act-pair · gpt-3.5-turbo

    references to social groups and familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceFile
    -0.60
    maxwell
    -0.58
    rez
    -0.56
    chev
    -0.54
    onen
    -0.54
     looph
    -0.53
    efficients
    -0.51
    EStream
    -0.51
    Ĥİ
    -0.51
    kernel
    -0.51
    POSITIVE LOGITS
     alike
    1.46
     respectively
    0.92
     thereof
    0.89
     versa
    0.86
     accordingly
    0.72
     thereto
    0.65
     thereafter
    0.60
     outfits
    0.58
     consequ
    0.58
     therein
    0.55
    Activations Density 1.578%

    No Known Activations