© 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. 20390
    Prev
    Next
    INDEX
    Explanations

    phrases related to things or concepts finding their proper place or position within a certain context

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "place" or "placement" in various contexts

    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
    ripp
    -0.71
    flix
    -0.64
     Traffic
    -0.58
     weeds
    -0.57
    edes
    -0.56
    reflect
    -0.56
     Sag
    -0.55
    inho
    -0.54
    Lev
    -0.54
    imar
    -0.54
    POSITIVE LOGITS
    holders
    0.92
    bos
    0.86
     atop
    0.85
    holder
    0.82
     holder
    0.73
    ktop
    0.71
    aterasu
    0.70
    senal
    0.70
     holders
    0.66
     amongst
    0.64
    Activations Density 0.106%

    No Known Activations