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. 10-RES-JB
    6. 18021
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or conditions that are intense or extreme

    oai_token-act-pair · gpt-3.5-turbo

    variations of the phrase "full-blown" in various contexts

    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
     Pok
    -0.75
     Tycoon
    -0.69
    Ń·
    -0.68
     Mystic
    -0.65
     charms
    -0.64
     Lum
    -0.63
     Woodward
    -0.61
     Conquer
    -0.60
     Miko
    -0.60
     Phi
    -0.60
    POSITIVE LOGITS
    fledged
    1.71
    blown
    1.43
    length
    1.34
    scale
    1.33
    sized
    1.31
    bodied
    1.27
    blooded
    1.21
    time
    1.17
    contact
    1.16
    court
    1.14
    Activations Density 0.023%

    No Known Activations