© 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. 9-RES-JB
    11. 15806
    Prev
    Next
    INDEX
    Explanations

    exclamatory statements and commands

    oai_token-act-pair · gpt-3.5-turbo

    phrases or expressions indicating strong emotional reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reclaimed
    -0.74
     metic
    -0.74
     conj
    -0.71
     preserved
    -0.70
     featured
    -0.68
     recomb
    -0.68
     tangled
    -0.67
     fused
    -0.67
     targeted
    -0.67
     entangled
    -0.67
    POSITIVE LOGITS
    Hey
    1.09
    Everybody
    1.04
    everyone
    1.04
    why
    1.04
    please
    1.03
    Look
    1.01
    Okay
    1.00
    nob
    0.98
    there
    0.96
    everything
    0.96
    Activations Density 0.047%

    No Known Activations