© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 13454
    Prev
    Next
    INDEX
    Explanations

    specific named entities such as people, organizations, and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to actions and statements made by individuals, particularly in a reporting context

    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
     Whilst
    -0.74
    Translation
    -0.74
     whilst
    -0.72
    Firstly
    -0.65
    uably
    -0.61
     genius
    -0.60
    200000
    -0.59
    Years
    -0.58
     hilarious
    -0.58
    @@@@@@@@
    -0.58
    POSITIVE LOGITS
     declined
    1.39
     said
    1.09
     thanked
    1.04
     spokeswoman
    1.01
     did
    0.98
     also
    0.95
     cautioned
    0.92
     praised
    0.88
     apologized
    0.87
     wouldn
    0.87
    Activations Density 0.436%

    No Known Activations