© 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. 1051
    Prev
    Next
    INDEX
    Explanations

    financial and technical terms relating to business and operations

    oai_token-act-pair · gpt-3.5-turbo

    specific terms related to administrative and structural processes

    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
    doms
    -0.73
    SPONSORED
    -0.72
    $.
    -0.68
     Houses
    -0.65
     Blacks
    -0.62
    zees
    -0.62
     Walls
    -0.62
     Gods
    -0.60
    eways
    -0.59
    Frames
    -0.59
    POSITIVE LOGITS
     emerges
    1.00
     awaits
    0.95
     exists
    0.91
     consists
    0.90
     ensued
    0.90
     arises
    0.81
     weighs
    0.79
     sprang
    0.79
     emerged
    0.79
     hangs
    0.78
    Activations Density 0.642%

    No Known Activations