© 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. 9-RES-JB
    11. 8905
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "ama" with varying levels of activation (7, 8, 9, or 10)

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "ama" and its variations, likely indicating a focus on content related to place names or identifiers

    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
    ting
    -1.04
    ted
    -0.96
    tle
    -0.78
    ttes
    -0.76
    meyer
    -0.75
    teenth
    -0.75
    points
    -0.74
    rers
    -0.74
    ried
    -0.73
    ters
    -0.72
    POSITIVE LOGITS
    ican
    1.02
    ña
    0.99
    é¾įåĸļ士
    0.93
    utra
    0.93
    eli
    0.91
    iah
    0.88
    qua
    0.86
    udeau
    0.85
    ñ
    0.84
    eus
    0.82
    Activations Density 0.065%

    No Known Activations