© 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. 5185
    Prev
    Next
    INDEX
    Explanations

    phrases related to team collaborations or line-ups

    oai_token-act-pair · gpt-3.5-turbo

    hyphenated phrases or compound terms

    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
    qus
    -0.69
     Ell
    -0.68
     Ces
    -0.66
     blackmail
    -0.63
     parchment
    -0.63
    Downloadha
    -0.62
     payday
    -0.60
     Ri
    -0.59
     divor
    -0.59
     Miss
    -0.58
    POSITIVE LOGITS
    sized
    1.13
    based
    1.08
    wide
    1.05
    level
    1.05
    specific
    0.99
    oriented
    0.99
    mode
    0.97
    manager
    0.95
    mates
    0.95
    saving
    0.94
    Activations Density 0.073%

    No Known Activations