© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 11411
    Prev
    Next
    INDEX
    Explanations

    keywords related to computer programming and data structures

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and concepts related to data analysis and comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sorely
    -0.72
     urgently
    -0.63
     Ambro
    -0.60
     kindred
    -0.59
     IMAGES
    -0.59
     flanked
    -0.57
     recomm
    -0.56
     understandably
    -0.55
     âĢİ
    -0.55
     behold
    -0.55
    POSITIVE LOGITS
     versa
    0.80
    ozy
    0.72
    politics
    0.68
    .?
    0.67
    pees
    0.66
    paren
    0.66
     ones
    0.66
    pol
    0.65
    emouth
    0.65
    mods
    0.64
    Activations Density 0.862%

    No Known Activations