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. 10-RES-JB
    6. 8752
    Prev
    Next
    INDEX
    Explanations

    strings of numbers like phone numbers or coordinates

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     newsp
    -0.66
     firsthand
    -0.62
     Ness
    -0.59
     existence
    -0.55
     compan
    -0.55
     ASS
    -0.53
     trade
    -0.52
     overnight
    -0.51
     fast
    -0.51
     exch
    -0.50
    POSITIVE LOGITS
    052
    1.33
    271
    1.31
    040
    1.30
    045
    1.30
    471
    1.30
    055
    1.29
    472
    1.28
    048
    1.28
    035
    1.28
    783
    1.28
    Activations Density 0.087%

    No Known Activations