© 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. 11-RES-JB
    11. 14988
    Prev
    Next
    INDEX
    Explanations

    symbols and special characters

    oai_token-act-pair · gpt-3.5-turbo

    notations or symbols that signify emphasis or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anse
    -0.70
     manif
    -0.69
     bore
    -0.65
     delinqu
    -0.65
    âĢ²
    -0.63
     lawn
    -0.63
     buoy
    -0.62
    omorphic
    -0.62
     reson
    -0.62
     wave
    -0.62
    POSITIVE LOGITS
    NEW
    1.12
    Names
    1.08
    NOTE
    1.06
     Required
    1.05
    Insert
    1.00
    UPDATE
    1.00
     *
    0.98
    Note
    0.97
    Correction
    0.96
    TEXT
    0.95
    Activations Density 0.029%

    No Known Activations