© 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 EvalsExportsAPI 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. 10-RES-JB
    11. 3374
    Prev
    Next
    INDEX
    Explanations

    references to downloadable content, such as files, code, and reports

    oai_token-act-pair · gpt-3.5-turbo

    terms related to downloading software or files

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     friendships
    -0.72
     afterlife
    -0.70
    anship
    -0.69
     interactions
    -0.68
    ciplinary
    -0.67
     distinction
    -0.66
     heightened
    -0.65
    roads
    -0.64
     endeav
    -0.64
     funer
    -0.64
    POSITIVE LOGITS
     pdf
    1.28
     PDF
    1.26
     ZIP
    1.22
    PDF
    1.17
    DragonMagazine
    1.15
     Download
    1.13
     downloaded
    1.13
     zip
    1.08
    pdf
    1.08
     download
    1.07
    Activations Density 0.175%

    No Known Activations