© 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. 2-RES-JB
    11. 7182
    Prev
    Next
    INDEX
    Explanations

    time stamps in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    sequences related to time or timestamps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enthusi
    -0.92
     advis
    -0.89
     behavi
    -0.89
    etheless
    -0.87
     entreprene
    -0.86
     glim
    -0.83
     rall
    -0.82
     undermin
    -0.81
     perspect
    -0.80
     volunte
    -0.79
    POSITIVE LOGITS
    jpg
    1.10
    htm
    1.01
    html
    1.00
    0
    0.96
    sbm
    0.95
    dll
    0.93
    5
    0.92
    png
    0.91
    length
    0.91
    exe
    0.89
    Activations Density 0.484%

    No Known Activations