© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16707
    Prev
    Next
    INDEX
    Explanations

    numbers related to hours and years

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to continuous time surveillance or 24-hour operations

    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
    oslav
    -0.71
    arnaev
    -0.71
    achus
    -0.71
    apult
    -0.71
    boa
    -0.70
    ificant
    -0.69
    regor
    -0.69
    etsk
    -0.67
    olate
    -0.65
     Dull
    -0.65
    POSITIVE LOGITS
    PsyNetMessage
    0.83
    ottest
    0.77
     Marketable
    0.70
    hour
    0.69
    ruary
    0.66
    00
    0.66
    fm
    0.66
    reviewed
    0.66
    illet
    0.65
    displayText
    0.63
    Activations Density 0.231%

    No Known Activations