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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 5885
    Prev
    Next
    INDEX
    Explanations

    expressions of emotions and opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotions related to sadness and disappointment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     veter
    -0.64
     rgb
    -0.60
     breathe
    -0.59
    ãĥĢ
    -0.56
     jew
    -0.56
    ¥
    -0.56
     dexterity
    -0.55
     coats
    -0.55
     ages
    -0.52
     assures
    -0.52
    POSITIVE LOGITS
    fman
    0.73
     Unch
    0.71
     Lank
    0.69
    pread
    0.68
     Schw
    0.66
     Cla
    0.61
     Stephenson
    0.61
    DonaldTrump
    0.61
     Peterson
    0.61
     DeVos
    0.59
    Activations Density 1.961%

    No Known Activations