© 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. 7-RES-JB
    11. 21186
    Prev
    Next
    INDEX
    Explanations

    instances where a task or action is being suggested or recommended

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "you have."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oshi
    -0.72
    inance
    -0.61
    ensing
    -0.57
     Voters
    -0.57
    ynski
    -0.57
    awa
    -0.56
    ickle
    -0.56
     reflects
    -0.55
     outp
    -0.55
    etting
    -0.54
    POSITIVE LOGITS
     been
    1.04
     gotten
    0.97
    been
    0.91
     recourse
    0.88
     plenty
    0.83
    drawn
    0.82
     pockets
    0.82
     nightmares
    0.81
     eaten
    0.81
     access
    0.80
    Activations Density 0.352%

    No Known Activations