© 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. 7800
    Prev
    Next
    INDEX
    Explanations

    words related to names or titles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the suffix "ath" in various 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
     Reloaded
    -0.79
    ITED
    -0.77
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.74
     shorth
    -0.73
     Gemini
    -0.64
    ebus
    -0.64
    LOAD
    -0.64
    hift
    -0.64
     Petraeus
    -0.64
    enhagen
    -0.63
    POSITIVE LOGITS
    aniel
    1.07
    urst
    1.04
    ouse
    0.97
    reshold
    0.94
    lete
    0.90
    iop
    0.90
    omas
    0.89
    itect
    0.88
    alon
    0.88
    opter
    0.87
    Activations Density 0.028%

    No Known Activations