© 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. 0-RES-JB
    6. 17919
    Prev
    Next
    INDEX
    Explanations

    names related to a specific theme, possibly related to locations or individuals

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of specific names and terms related to Taronga Zoo and notable individuals associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kerry
    -0.80
     Lerner
    -0.68
    metic
    -0.66
    ×Ļ×
    -0.65
    moon
    -0.64
    internal
    -0.60
    BG
    -0.60
    arity
    -0.59
    intern
    -0.58
    Letter
    -0.58
    POSITIVE LOGITS
    onga
    4.63
    orio
    1.60
    tein
    1.49
    uca
    1.27
    iji
    1.23
    egu
    1.13
     Maker
    1.09
    wi
    1.06
    rosse
    1.04
    WI
    0.93
    Activations Density 0.034%

    No Known Activations