© 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 EvalsExportsinterp-engineNEWAPI 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. 21047
    Prev
    Next
    INDEX
    Explanations

    statements or documents that have been formally released or issued

    oai_token-act-pair · gpt-3.5-turbo

    terms related to formal communications or announcements

    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
     Conquer
    -0.56
     Decay
    -0.54
    involved
    -0.51
    atever
    -0.50
     Champion
    -0.50
    tumblr
    -0.49
    SET
    -0.49
     civilisation
    -0.48
     TOD
    -0.48
     ascended
    -0.48
    POSITIVE LOGITS
     Tuesday
    1.21
     Wednesday
    1.20
     Monday
    1.18
     Thursday
    1.18
     Friday
    1.13
    nesday
    1.07
     yesterday
    1.06
     by
    1.04
     jointly
    1.01
     Sunday
    1.00
    Activations Density 0.094%

    No Known Activations