© 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. 22110
    Prev
    Next
    INDEX
    Explanations

    phrases related to computer code

    oai_token-act-pair · gpt-3.5-turbo

    sequences of specific characters or symbols

    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
    ĸļ
    -0.96
    awaru
    -0.86
    kers
    -0.83
    ngth
    -0.80
    ffield
    -0.79
    eson
    -0.79
    earchers
    -0.78
    nyder
    -0.76
    */(
    -0.75
    omnia
    -0.73
    POSITIVE LOGITS
    âĶĢâĶĢ
    1.25
    âĶĢâĶĢâĶĢâĶĢ
    1.09
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.98
    âĶĢ
    0.95
    âķIJâķIJ
    0.94
    Ķ
    0.93
    ت
    0.90
    Ùĩ
    0.88
    aneously
    0.87
    س
    0.86
    Activations Density 0.004%

    No Known Activations