© 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. 4-RES-JB
    6. 24256
    Prev
    Next
    INDEX
    Explanations

    questions starting with "Can"

    oai_token-act-pair · gpt-3.5-turbo

    questions that begin with "Can."

    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
     thirds
    -0.64
     CPI
    -0.64
    direction
    -0.64
     chasing
    -0.63
    edient
    -0.63
     striving
    -0.62
     rehearsal
    -0.60
     banging
    -0.57
    hran
    -0.57
    VERTISEMENT
    -0.57
    POSITIVE LOGITS
    't
    1.45
    berra
    1.14
    NOT
    1.05
    adian
    1.03
    isters
    0.90
    opy
    0.87
    ADA
    0.86
    ny
    0.86
    vas
    0.86
    icum
    0.81
    Activations Density 0.063%

    No Known Activations