© 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. 4-RES-JB
    11. 18641
    Prev
    Next
    INDEX
    Explanations

    mentions related to a specific fictional or organization name, "Aggie"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Aggie," likely referring to a mascot or group identity

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

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.86
    代
    -0.81
    phrine
    -0.76
    çīĪ
    -0.75
    姫
    -0.75
     sights
    -0.69
    neck
    -0.67
    HCR
    -0.64
    çĦ
    -0.63
    */(
    -0.62
    POSITIVE LOGITS
    regate
    1.40
    ressive
    1.23
    Agg
    1.14
    ressor
    1.05
    raph
    0.96
    ression
    0.95
    regation
    0.93
    rieved
    0.91
    irlf
    0.87
    regn
    0.86
    Activations Density 0.013%

    No Known Activations