© 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. 17247
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical locations or descriptive adjectives

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns and their related concepts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     neut
    -0.57
    udeb
    -0.57
     respons
    -0.52
     bursting
    -0.51
     behold
    -0.51
     history
    -0.50
     Mich
    -0.49
     sheet
    -0.48
     falling
    -0.47
     disg
    -0.47
    POSITIVE LOGITS
    kefeller
    0.78
    olars
    0.76
    algia
    0.75
    terness
    0.75
    apy
    0.71
    tainment
    0.68
    heid
    0.65
    utenant
    0.65
    ipel
    0.64
    uthor
    0.64
    Activations Density 0.274%

    No Known Activations