© 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. 4-RES-JB
    6. 4429
    Prev
    Next
    INDEX
    Explanations

    references to individuals interested in niche topics or hobbies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to 'nerd' and 'geek' culture

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

    No Comments

    Negative Logits
     terminating
    -0.73
    ugal
    -0.73
    undai
    -0.71
    comings
    -0.68
    utions
    -0.68
     Parenthood
    -0.68
     Liberties
    -0.67
     abortions
    -0.66
     insurers
    -0.65
     opposing
    -0.64
    POSITIVE LOGITS
     geek
    0.95
     nerd
    0.93
    Crunch
    0.87
     nerds
    0.82
    hack
    0.80
    sonian
    0.78
    hattan
    0.78
    linger
    0.78
    core
    0.76
    beans
    0.76
    Activations Density 0.018%

    No Known Activations