© 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. 9183
    Prev
    Next
    INDEX
    Explanations

    technical actions related to software development and computer operations

    oai_token-act-pair · gpt-3.5-turbo

    actions related to technical processes or activities, particularly in computing and outdoor contexts

    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
    quart
    -0.74
    yson
    -0.72
    vu
    -0.70
    xus
    -0.69
    ties
    -0.67
    cci
    -0.66
    si
    -0.65
    iere
    -0.65
    pps
    -0.64
    gow
    -0.63
    POSITIVE LOGITS
    HAM
    1.06
     oneself
    1.03
    redients
    0.97
     prowess
    0.79
     techniques
    0.78
     spree
    0.76
     purposes
    0.74
     machines
    0.74
     sessions
    0.70
     tools
    0.69
    Activations Density 0.349%

    No Known Activations