Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 12-RES-JB
    6. 7006
    Prev
    Next
    INDEX
    Explanations

    instances where the word 'only' is used

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of the word "only."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    neum
    -0.77
    iller
    -0.74
    none
    -0.71
    haven
    -0.69
    ongs
    -0.67
    vantage
    -0.65
    psc
    -0.64
    clerosis
    -0.63
    opsy
    -0.63
    rug
    -0.63
    POSITIVE LOGITS
     marginally
    0.99
     scratching
    0.91
     halfway
    0.83
     pretending
    0.81
     moderately
    0.81
     kidding
    0.81
     joking
    0.80
     temporary
    0.79
    ifiable
    0.78
     peripher
    0.77
    Activations Density 0.055%

    No Known Activations