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. 4-RES-JB
    6. 5567
    Prev
    Next
    INDEX
    Explanations

    words related to expectations being met or not

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express a sense of expectation or anticipation

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

    No Comments

    Negative Logits
     Christy
    -0.63
    phone
    -0.62
    va
    -0.58
     McA
    -0.57
    uish
    -0.57
     Erie
    -0.57
    onite
    -0.55
    kos
    -0.54
     Loren
    -0.54
     Sullivan
    -0.54
    POSITIVE LOGITS
    lege
    0.64
    azeera
    0.64
    IDENT
    0.61
    rike
    0.60
    cffffcc
    0.59
    eas
    0.57
    ALSE
    0.57
    eyes
    0.57
    glomer
    0.56
    icted
    0.56
    Activations Density 0.175%

    No Known Activations