© 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. 24034
    Prev
    Next
    INDEX
    Explanations

    pronouns and their related actions

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of placing or handling objects

    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
     understatement
    -0.68
    roads
    -0.61
     Kelley
    -0.60
    ofer
    -0.56
     Founding
    -0.55
     Miguel
    -0.55
     Polk
    -0.55
     Cars
    -0.55
     Paso
    -0.55
     Balt
    -0.54
    POSITIVE LOGITS
    anwhile
    0.91
    alian
    0.85
    atic
    0.83
     accordingly
    0.82
     onto
    0.79
    ividual
    0.73
     into
    0.73
     overboard
    0.73
    self
    0.72
    essage
    0.70
    Activations Density 0.147%

    No Known Activations