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. 14923
    Prev
    Next
    INDEX
    Explanations

    ownership-related actions or details

    oai_token-act-pair · gpt-3.5-turbo

    actions or states related to ownership and legal processes

    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
     guiActiveUn
    -0.63
    ãĥĻ
    -0.56
    eu
    -0.55
    ongh
    -0.54
    ãĥ¼ãĥ«
    -0.53
    horn
    -0.52
    arist
    -0.50
    Enabled
    -0.47
    ãĤ»
    -0.47
    uld
    -0.46
    POSITIVE LOGITS
     ..........
    0.52
     both
    0.48
     [[
    0.47
     several
    0.46
    uate
    0.46
     McDonnell
    0.45
     TWO
    0.44
     ..............
    0.44
     Mn
    0.43
     âĢİ
    0.43
    Activations Density 1.353%

    No Known Activations