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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3838
    Prev
    Next
    INDEX
    Explanations

    instances where the document talks about expansion or growth

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "expand"

    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
    nee
    -0.74
     Alone
    -0.68
    fell
    -0.67
     Chance
    -0.64
    */(
    -0.64
    DER
    -0.63
     Upton
    -0.63
    knife
    -0.62
    Ale
    -0.62
    die
    -0.62
    POSITIVE LOGITS
    ĸļ
    0.93
     expansion
    0.85
    glomer
    0.79
     expands
    0.79
     enlarg
    0.77
    acebook
    0.77
     expand
    0.77
     expanding
    0.74
     expansions
    0.73
    onential
    0.72
    Activations Density 0.009%

    No Known Activations