© 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. 9-RES-JB
    6. 13706
    Prev
    Next
    INDEX
    Explanations

    words related to algorithms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of algorithms

    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
    lihood
    -0.75
    shirt
    -0.69
    holders
    -0.69
    joy
    -0.69
     quarters
    -0.67
    abouts
    -0.65
    igi
    -0.63
     Episode
    -0.62
    holder
    -0.61
     Banner
    -0.61
    POSITIVE LOGITS
    ically
    1.21
    atically
    0.94
    ical
    0.90
    icity
    0.88
     algorithms
    0.86
    atic
    0.83
    ics
    0.83
    onite
    0.82
     devised
    0.81
     algorithm
    0.81
    Activations Density 0.048%

    No Known Activations