© 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. 0-RES-JB
    6. 20146
    Prev
    Next
    INDEX
    Explanations

    keyboard shortcuts related to the Shift key

    oai_token-act-pair · gpt-3.5-turbo

    computer commands and technical notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brook
    -0.67
     mature
    -0.66
     prom
    -0.64
     sandy
    -0.64
    rom
    -0.64
    angel
    -0.64
    mie
    -0.63
     Pon
    -0.63
     collection
    -0.63
     surve
    -0.63
    POSITIVE LOGITS
     Ctrl
    3.26
    Ctrl
    2.57
     CTRL
    1.89
    ¢
    1.81
     Shift
    1.76
    ctrl
    1.76
    trl
    1.67
    Shift
    1.51
    sudo
    1.25
     sudo
    1.20
    Activations Density 0.063%

    No Known Activations