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. 6-RES-JB
    6. 21624
    Prev
    Next
    INDEX
    Explanations

    instances containing the word "will" or "ll" followed by an action verb

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases indicating intent or planned actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActiveUn
    -0.71
    CTV
    -0.64
    quickShipAvailable
    -0.64
    cription
    -0.62
    lished
    -0.62
     è£ıç
    -0.60
     Measures
    -0.59
     Kou
    -0.59
     Critics
    -0.58
    Song
    -0.58
    POSITIVE LOGITS
    uminati
    1.27
    inois
    1.05
    oyd
    1.02
    ounge
    0.94
    owship
    0.89
    umin
    0.88
    ibrary
    0.87
    uci
    0.86
    iard
    0.84
    ibr
    0.81
    Activations Density 0.023%

    No Known Activations