© 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. 6241
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and data, predominantly focusing on computer operations and internet-related actions

    oai_token-act-pair · gpt-3.5-turbo

    various types of nouns and actions related to events, objects, and rules

    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
    something
    -0.47
     Thompson
    -0.46
     Norris
    -0.46
    âĸ¬
    -0.44
    ÃŃs
    -0.43
     circumstance
    -0.43
    mer
    -0.42
    athan
    -0.41
    Witness
    -0.41
    Buzz
    -0.41
    POSITIVE LOGITS
    ource
    1.11
    afety
    1.06
    ettings
    1.06
    heet
    1.06
    peed
    1.04
    ystem
    1.03
    etting
    1.00
    paces
    0.98
    ync
    0.96
    mith
    0.95
    Activations Density 0.234%

    No Known Activations