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. 7-RES-JB
    6. 16070
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'sticky' or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    words that are adjectives relating to a negative or unpleasant quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iation
    -1.05
    iations
    -0.93
    ials
    -0.89
    inals
    -0.87
    ational
    -0.84
    iated
    -0.82
    owment
    -0.81
    ial
    -0.79
    inators
    -0.78
    encers
    -0.77
    POSITIVE LOGITS
    weed
    1.05
    butt
    0.93
    pants
    0.91
     Kong
    0.90
     Doodle
    0.87
     Dick
    0.79
    foot
    0.78
    bilt
    0.77
    chief
    0.77
     Isles
    0.75
    Activations Density 0.164%

    No Known Activations