© 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
    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. 3089
    Prev
    Next
    INDEX
    Explanations

    parentheses indicating code-related expressions

    oai_token-act-pair · gpt-3.5-turbo

    parentheses and other opening/closing symbols commonly used in code

    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
    leep
    -0.78
     impeachment
    -0.76
     minded
    -0.75
    earch
    -0.74
    ettings
    -0.74
    isodes
    -0.70
    ĵĺ
    -0.69
    undown
    -0.69
     whip
    -0.69
     seasonal
    -0.68
    POSITIVE LOGITS
    ...)
    1.00
    partial
    0.93
    optional
    0.88
    src
    0.87
    excluding
    0.84
    shown
    0.83
    sic
    0.82
     )
    0.82
    aka
    0.81
    ())
    0.81
    Activations Density 0.115%

    No Known Activations