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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 3-RES-JB
    6. 952
    Prev
    Next
    INDEX
    Explanations

    proper names related to different individuals named Johansen

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Joh" and its variations in the text

    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
    dress
    -0.85
    PLIED
    -0.84
     subsistence
    -0.76
    holders
    -0.76
    uyomi
    -0.75
    20439
    -0.74
    ranean
    -0.70
    ULTS
    -0.68
    pmwiki
    -0.66
    intendent
    -0.66
    POSITIVE LOGITS
    ansson
    1.27
    ansen
    1.21
     Joh
    1.04
    ani
    1.03
    anes
    0.97
    sin
    0.88
    anna
    0.88
    anson
    0.88
    annah
    0.87
    ans
    0.87
    Activations Density 0.007%

    No Known Activations