© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 4976
    Prev
    Next
    INDEX
    Explanations

    sports-related events and scores

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and indications of transitions between events or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.72
    izen
    -0.72
    ibilities
    -0.69
     Examples
    -0.69
    yll
    -0.68
    azeera
    -0.66
    =\"
    -0.65
    scribe
    -0.65
    ire
    -0.63
    inate
    -0.63
    POSITIVE LOGITS
     defeating
    1.23
     beating
    1.08
     securing
    1.03
     finishing
    1.02
     dropping
    1.01
     earning
    1.01
     ending
    1.00
     knocking
    0.99
     losing
    0.98
     overcoming
    0.97
    Activations Density 0.157%

    No Known Activations