© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 12487
    Prev
    Next
    INDEX
    Explanations

    words related to names, particularly those ending with the letter 'i'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'i'

    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
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.75
    pter
    -0.69
     Typh
    -0.65
     convol
    -0.65
    cffff
    -0.65
     colleg
    -0.64
     Valkyrie
    -0.64
     Compass
    -0.61
     alternate
    -0.60
     Haunted
    -0.60
    POSITIVE LOGITS
    orno
    1.05
    uli
    1.05
    ota
    1.04
    ibo
    1.01
    ye
    0.99
    oti
    0.99
    ñ
    0.99
    hee
    0.98
    ogi
    0.97
    wa
    0.97
    Activations Density 0.049%

    No Known Activations