© 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. 3-RES-JB
    11. 1575
    Prev
    Next
    INDEX
    Explanations

    references to the location "Tamaulipas" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    the word "ama" and its variations, likely indicating a focus on familial connections or contexts related to "mother."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ting
    -0.89
    tle
    -0.82
    points
    -0.79
    ted
    -0.76
    sheet
    -0.74
    teenth
    -0.71
    ther
    -0.71
    ried
    -0.69
     clipboard
    -0.66
    working
    -0.66
    POSITIVE LOGITS
    ña
    0.98
    ican
    0.97
    qua
    0.97
    ñ
    0.95
    uthor
    0.92
    ama
    0.89
    udeau
    0.86
    zzle
    0.84
    ption
    0.83
    icans
    0.80
    Activations Density 0.008%

    No Known Activations