© 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. 10-RES-JB
    11. 13554
    Prev
    Next
    INDEX
    Explanations

    references to dogs

    oai_token-act-pair · gpt-3.5-turbo

    references to dogs and canine-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Animals

    No Comments

    Negative Logits
    esson
    -0.94
    DERR
    -0.80
    velength
    -0.80
    artz
    -0.79
    éĹĺ
    -0.77
     WARN
    -0.73
     Edison
    -0.71
    ISTER
    -0.70
    erences
    -0.68
    unda
    -0.66
    POSITIVE LOGITS
    gie
    1.18
     barking
    1.15
    fighting
    1.09
    fight
    1.07
    fights
    1.03
    meat
    1.01
    matic
    0.99
    shit
    0.97
    fighter
    0.97
     catcher
    0.95
    Activations Density 0.038%

    No Known Activations