© 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. 1-RES-JB
    11. 2038
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Ant"

    oai_token-act-pair · gpt-3.5-turbo

    the word "Ant" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UTION
    -0.94
    FORMATION
    -0.93
    ESSION
    -0.77
    =-=-=-=-
    -0.77
    UGE
    -0.76
    wagen
    -0.75
    )=(
    -0.75
    SIGN
    -0.74
    OURCE
    -0.74
    20439
    -0.71
    POSITIVE LOGITS
    agonists
    0.91
    oine
    0.91
    ico
    0.90
     Ant
    0.90
    iques
    0.89
    heon
    0.88
    enna
    0.87
    agonist
    0.85
    ioxid
    0.85
    idepress
    0.85
    Activations Density 0.007%

    No Known Activations