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. 7426
    Prev
    Next
    INDEX
    Explanations

    links or instructions indicated by the word "here"

    oai_token-act-pair · gpt-3.5-turbo

    calls to action, specifically instances of the phrase "click here."

    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
    omore
    -0.70
    itialized
    -0.66
    ONSORED
    -0.63
     Heights
    -0.60
    utter
    -0.59
    visors
    -0.58
    ggle
    -0.58
    iven
    -0.58
    cig
    -0.57
     Breath
    -0.56
    POSITIVE LOGITS
    tics
    1.32
    tical
    1.25
    abouts
    1.13
    tic
    1.12
    here
    0.83
     guiActiveUn
    0.81
     newsp
    0.72
     âĨij
    0.68
    utherland
    0.67
     .)
    0.65
    Activations Density 0.053%

    No Known Activations