© 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. 10-RES-JB
    11. 11014
    Prev
    Next
    INDEX
    Explanations

    mentions of achievements and accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    prepositions indicating location or context

    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
     oneself
    -0.80
     yourselves
    -0.79
    ratulations
    -0.68
    arently
    -0.67
    ecause
    -0.66
    rehensive
    -0.64
     yourself
    -0.64
    Its
    -0.64
    acci
    -0.62
    rets
    -0.61
    POSITIVE LOGITS
     fame
    0.81
     activism
    0.77
     glory
    0.71
     captivity
    0.67
     filmmaking
    0.65
     life
    0.62
     riches
    0.62
    ãĤ¨ãĥ«
    0.62
     prominence
    0.62
    thood
    0.61
    Activations Density 0.327%

    No Known Activations