© 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. 0-RES-JB
    11. 16340
    Prev
    Next
    INDEX
    Explanations

    words related to the term "utt" which could potentially be part of a proper noun

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the substring "utt" within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     metal
    -0.71
     chemistry
    -0.65
     neighbors
    -0.62
     ourselves
    -0.60
     brothers
    -0.59
     metals
    -0.59
     Henry
    -0.58
     lottery
    -0.57
     symbol
    -0.57
     semic
    -0.57
    POSITIVE LOGITS
    utt
    4.67
    uts
    1.45
    uti
    1.40
    ut
    1.35
    utton
    1.30
    utter
    1.27
    utor
    1.23
    utters
    1.21
    uto
    1.18
    utra
    1.15
    Activations Density 0.017%

    No Known Activations