© 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. 9486
    Prev
    Next
    INDEX
    Explanations

    phrases indicating interest or focus

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "to" that indicate intention or purpose

    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
    arten
    -0.69
     umb
    -0.66
     cass
    -0.65
     refunds
    -0.63
     freezing
    -0.60
     exemptions
    -0.60
    opus
    -0.60
     signaled
    -0.59
    awei
    -0.59
    unn
    -0.59
    POSITIVE LOGITS
    ggles
    0.99
     behold
    0.90
    mes
    0.85
     contemplate
    0.84
    pper
    0.79
    ADS
    0.77
    me
    0.75
    asts
    0.74
    ilet
    0.74
    roe
    0.71
    Activations Density 0.128%

    No Known Activations