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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 12063
    Prev
    Next
    INDEX
    Explanations

    terms related to governmental agencies, political figures, and technology

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the end of content marker

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Niet
    -0.64
     Peb
    -0.56
     Rober
    -0.52
     prest
    -0.51
     Berm
    -0.51
     Siber
    -0.51
     Vaugh
    -0.51
     Nanto
    -0.50
     Krug
    -0.49
     Azerb
    -0.48
    POSITIVE LOGITS
     reacts
    0.59
     approves
    0.52
     âĢº
    0.50
     doesnt
    0.50
     |
    0.48
     sucks
    0.47
     hoax
    0.46
     adjusts
    0.46
     kills
    0.46
    ":{"
    0.46
    Activations Density 0.782%

    No Known Activations