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. 4-RES-JB
    6. 9862
    Prev
    Next
    INDEX
    Explanations

    descriptions of things as "nice"

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "nice."

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

    No Comments

    Negative Logits
    arians
    -0.79
    ogens
    -0.79
    authorized
    -0.79
    arers
    -0.76
    arian
    -0.75
    ochond
    -0.75
    inant
    -0.74
    rained
    -0.74
    uilding
    -0.71
    igate
    -0.69
    POSITIVE LOGITS
     nice
    0.92
     bye
    0.86
     fluffy
    0.81
    bye
    0.80
     touches
    0.78
     additions
    0.78
     little
    0.75
     enough
    0.75
     neat
    0.74
     bonus
    0.74
    Activations Density 0.019%

    No Known Activations