© 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. 7-RES-JB
    11. 20675
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific technical terms

    oai_token-act-pair · gpt-3.5-turbo

    specific types of roles or positions tied to authority or responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interchange
    -0.88
     vested
    -0.71
     metaphor
    -0.66
     correspondent
    -0.65
     uphill
    -0.64
     refrain
    -0.64
     infringing
    -0.63
     equilibrium
    -0.62
     respons
    -0.62
     dimin
    -0.62
    POSITIVE LOGITS
    ater
    1.00
    aris
    0.97
    ī
    0.94
    xes
    0.94
    ctions
    0.94
    ques
    0.94
    aker
    0.91
    ases
    0.91
    OME
    0.90
    ante
    0.90
    Activations Density 0.729%

    No Known Activations