Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 9481
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions such as "karmic"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "k"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •words starting with k

    No Comments

    Negative Logits
    Ø©
    -0.82
    IBLE
    -0.79
    éĹĺ
    -0.74
    terday
    -0.70
     Malf
    -0.70
    ãĥ¼ãĥĨãĤ£
    -0.70
     expires
    -0.67
    ÙĴ
    -0.66
     Rica
    -0.66
     Staples
    -0.66
    POSITIVE LOGITS
    idd
    1.27
    itty
    1.22
    ippers
    1.13
    appa
    1.12
    etchup
    1.08
    ipp
    1.07
    ratom
    1.03
    irk
    1.01
    rieg
    1.00
    erry
    0.99
    Activations Density 0.022%

    No Known Activations