© 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. 1-RES-JB
    11. 20216
    Prev
    Next
    INDEX
    Explanations

    phrases related to exploring different options or choices

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to potential options and opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gar
    -0.78
    brand
    -0.76
    rix
    -0.75
    bey
    -0.74
    ric
    -0.70
    die
    -0.69
    roy
    -0.68
    tes
    -0.68
    ippy
    -0.68
    ger
    -0.67
    POSITIVE LOGITS
     possibilities
    1.19
     avenues
    0.95
    DragonMagazine
    0.90
    hift
    0.85
    ossibility
    0.85
     prospects
    0.83
     options
    0.81
     feas
    0.80
     elig
    0.77
    izons
    0.76
    Activations Density 0.003%

    No Known Activations