© 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. 5614
    Prev
    Next
    INDEX
    Explanations

    words related to actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    references to actions, dimensions, and functional characteristics

    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
    aren
    -0.76
     Torn
    -0.66
    letes
    -0.65
    sers
    -0.64
     Clintons
    -0.64
    illin
    -0.64
    regn
    -0.62
    oute
    -0.61
    ominated
    -0.60
    zzy
    -0.59
    POSITIVE LOGITS
     guise
    0.98
     form
    0.80
     manner
    0.80
     mode
    0.78
     fashion
    0.77
     shape
    0.72
    ividual
    0.70
     vicinity
    0.65
     proportions
    0.64
     staging
    0.64
    Activations Density 0.246%

    No Known Activations