© 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. 3-RES-JB
    11. 20958
    Prev
    Next
    INDEX
    Explanations

    special characters with hexadecimal representations

    oai_token-act-pair · gpt-3.5-turbo

    sequences that resemble a specific pattern or formatting, particularly those with slashes and variable-like structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     destro
    -0.88
    aimon
    -0.78
    theless
    -0.78
     Seym
    -0.77
    ascus
    -0.75
     insult
    -0.72
     crooked
    -0.72
     therap
    -0.71
     Jericho
    -0.69
     choked
    -0.68
    POSITIVE LOGITS
    AppData
    1.09
    (\
    0.95
    bryce
    0.91
    features
    0.88
    SpaceEngineers
    0.88
    Parameters
    0.87
    framework
    0.86
    Config
    0.84
    limits
    0.84
    resources
    0.84
    Activations Density 0.006%

    No Known Activations