© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 7785
    Prev
    Next
    INDEX
    Explanations

    words related to competition and events

    oai_token-act-pair · gpt-3.5-turbo

    references to specific entities, events, or concepts related to sports and community activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Built
    -0.66
    ãĥ¼ãĥĨãĤ£
    -0.63
    Specific
    -0.62
    Primary
    -0.61
    Frag
    -0.59
    Title
    -0.58
    Rap
    -0.57
    registered
    -0.57
    broad
    -0.56
     Pwr
    -0.55
    POSITIVE LOGITS
     syndrome
    0.92
    âĦ¢
    0.88
    !,
    0.77
     Syndrome
    0.72
     mentality
    0.70
     Productions
    0.67
    !.
    0.66
     fallacy
    0.66
     extraord
    0.65
    ppa
    0.63
    Activations Density 0.909%

    No Known Activations