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. 0-RES-JB
    6. 163
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to giving approval or agreement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "nod" and its variations, indicating agreement or acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    learn
    -0.69
    league
    -0.67
    iless
    -0.65
     Dest
    -0.65
     WITHOUT
    -0.64
    hours
    -0.64
    div
    -0.63
    î
    -0.63
     Exile
    -0.63
    life
    -0.62
    POSITIVE LOGITS
     nod
    4.31
     nods
    2.56
     nodding
    1.80
     wink
    1.61
     nodded
    1.58
     chuckle
    1.32
     salute
    1.22
     shrug
    1.21
     homage
    1.09
     thumbs
    1.07
    Activations Density 0.022%

    No Known Activations