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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7-RES-JB
    6. 22404
    Prev
    Next
    INDEX
    Explanations

    adjectives emphasizing completion or entirety

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "complete" in various forms, indicating themes of totality or finality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    maid
    -1.03
    hao
    -0.70
    ocene
    -0.70
    uay
    -0.69
    */(
    -0.69
    ker
    -0.65
    ãħĭ
    -0.64
    hops
    -0.64
    adish
    -0.63
    zsche
    -0.63
    POSITIVE LOGITS
     strangers
    0.92
    bred
    0.91
     Coverage
    0.84
    teness
    0.81
    rehensive
    0.80
     fabrication
    0.79
    itarian
    0.78
     stranger
    0.78
     immersion
    0.71
     absence
    0.70
    Activations Density 0.028%

    No Known Activations