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. 2697
    Prev
    Next
    INDEX
    Explanations

    names of specific locations or places, including cities and specific company names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "G" in various contexts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.72
    ĸļ
    -0.70
     htt
    -0.62
     craw
    -0.62
    oÄŁ
    -0.62
     Conquest
    -0.61
     vou
    -0.61
     retrospect
    -0.60
     sight
    -0.60
     Ruins
    -0.60
    POSITIVE LOGITS
    asp
    1.15
    ossip
    1.10
    irlfriend
    1.10
    oliath
    1.10
    iant
    1.08
    reetings
    1.06
    CHQ
    1.06
    ospels
    1.06
    reet
    1.05
    ather
    1.05
    Activations Density 0.048%

    No Known Activations