© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 20557
    Prev
    Next
    INDEX
    Explanations

    references to the word "yard"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "yard" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PsyNetMessage
    -0.79
    NetMessage
    -0.76
    oice
    -0.72
    onymous
    -0.71
    opsis
    -0.69
    ngth
    -0.69
    izophren
    -0.68
    ivia
    -0.68
    berus
    -0.65
    VIDIA
    -0.65
    POSITIVE LOGITS
    yard
    0.93
    birds
    0.90
    yards
    0.86
    enium
    0.85
    stones
    0.83
     yard
    0.83
    iage
    0.82
    bridge
    0.80
    stick
    0.80
    bage
    0.77
    Activations Density 0.030%

    No Known Activations