© 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. 6-RES-JB
    11. 2570
    Prev
    Next
    INDEX
    Explanations

    references to organizations or terms related to specific formal agreements or documents

    oai_token-act-pair · gpt-3.5-turbo

    references to charter schools

    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
    nesota
    -0.79
    pez
    -0.76
    encer
    -0.76
    Downloadha
    -0.75
    ewski
    -0.71
    ocate
    -0.69
     Rove
    -0.69
    encers
    -0.69
    ugs
    -0.68
    Lenin
    -0.66
    POSITIVE LOGITS
     Charter
    0.78
    icut
    0.78
     charter
    0.73
    fman
    0.70
     Bubble
    0.69
    zeb
    0.66
    iffs
    0.64
    neys
    0.64
    holder
    0.64
     entit
    0.63
    Activations Density 0.015%

    No Known Activations