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. 2-RES-JB
    6. 13355
    Prev
    Next
    INDEX
    Explanations

    references to specific online identities, possibly related to social media profiles

    oai_token-act-pair · gpt-3.5-turbo

    the word "sta" in various contexts, likely referencing a place or entity related to "statistical" or "station."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mented
    -0.76
    yll
    -0.75
    tein
    -0.72
    t
    -0.71
    ymm
    -0.71
    sticks
    -0.70
    layer
    -0.68
    egg
    -0.67
    mallow
    -0.67
     Oz
    -0.67
    POSITIVE LOGITS
    ignt
    0.88
    upid
    0.81
    zzle
    0.79
    quez
    0.79
    qs
    0.79
    igslist
    0.78
    pling
    0.77
    pps
    0.76
    essler
    0.75
    qt
    0.74
    Activations Density 0.011%

    No Known Activations