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. 3-RES-JB
    6. 1426
    Prev
    Next
    INDEX
    Explanations

    instances of actions or events done in a discreet or secretive manner

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "quietly."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amins
    -0.79
    rers
    -0.78
    gerald
    -0.77
    ragon
    -0.74
    iens
    -0.74
    rost
    -0.73
    ados
    -0.73
    oa
    -0.70
    eer
    -0.69
    ordan
    -0.66
    POSITIVE LOGITS
     bom
    0.86
    quiet
    0.78
     tucked
    0.78
     quietly
    0.76
     buried
    0.73
     dissip
    0.72
     quiet
    0.70
     unheard
    0.69
     Tradable
    0.68
    bda
    0.68
    Activations Density 0.008%

    No Known Activations