© 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. 6-RES-JB
    11. 5173
    Prev
    Next
    INDEX
    Explanations

    instances where something would have occurred or been done

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "would have," indicating hypothetical or conditional scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cold
    -0.60
     plaintiff
    -0.57
    osi
    -0.56
     poppy
    -0.56
     muse
    -0.56
     narrator
    -0.56
     seasoning
    -0.54
     doll
    -0.54
    Trivia
    -0.53
     hostage
    -0.53
    POSITIVE LOGITS
     been
    1.04
     gotten
    0.98
    been
    0.97
    ĸļ
    0.85
    ¶
    0.84
     taken
    0.83
    Ģ
    0.81
    gotten
    0.80
     gone
    0.77
     Been
    0.76
    Activations Density 0.067%

    No Known Activations