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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9-RES-JB
    11. 1554
    Prev
    Next
    INDEX
    Explanations

    names or references to names in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "name."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yrinth
    -0.81
    icult
    -0.76
    istar
    -0.73
    psey
    -0.72
    romy
    -0.71
    elaide
    -0.70
    isoft
    -0.68
    irth
    -0.66
    isexual
    -0.65
    berra
    -0.64
    POSITIVE LOGITS
    plates
    1.53
    plate
    1.46
    paces
    1.28
    paced
    1.03
    names
    0.89
     recognition
    0.89
    ames
    0.88
    brand
    0.87
    akes
    0.86
     lookup
    0.86
    Activations Density 0.046%

    No Known Activations