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. 9-RES-JB
    6. 22270
    Prev
    Next
    INDEX
    Explanations

    phrases that express a lack of surprise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases indicating lack of surprise or inevitability

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     raft
    -0.81
    abase
    -0.78
    pes
    -0.78
    ictionary
    -0.76
    ©¶æ
    -0.68
    edom
    -0.67
    ailability
    -0.67
     bowling
    -0.66
     fingert
    -0.65
     canoe
    -0.64
    POSITIVE LOGITS
    imaru
    0.69
     Pav
    0.69
     why
    0.66
     considering
    0.66
    EC
    0.63
    DragonMagazine
    0.62
     Tories
    0.58
     wonder
    0.58
     Opinion
    0.58
     Revelations
    0.57
    Activations Density 0.072%

    No Known Activations