© 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. 22285
    Prev
    Next
    INDEX
    Explanations

    the word "all" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    the word "all" in various contexts indicating totality or entirety

    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
    pload
    -0.69
    SHIP
    -0.67
    dt
    -0.66
    bye
    -0.65
     Riv
    -0.64
    plin
    -0.64
    isoft
    -0.63
     tremend
    -0.63
     Rouge
    -0.63
    icter
    -0.62
    POSITIVE LOGITS
    ocating
    1.22
    ocated
    1.04
    igators
    1.02
    usions
    0.99
    usion
    0.96
    igator
    0.96
    ocation
    0.95
    uding
    0.88
    iances
    0.86
    ocations
    0.86
    Activations Density 0.051%

    No Known Activations