© 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. 9530
    Prev
    Next
    INDEX
    Explanations

    short phrases that introduce or summarize information

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate summaries or overviews

    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
    anism
    -0.80
    ['
    -0.75
    acid
    -0.71
    same
    -0.71
    cair
    -0.70
    agents
    -0.69
     eg
    -0.68
    hes
    -0.68
    evidence
    -0.67
    alties
    -0.67
    POSITIVE LOGITS
     couple
    1.15
     few
    1.10
     glimpse
    1.09
     bunch
    1.07
     lot
    1.06
     handful
    1.02
    cknowled
    1.02
     slew
    0.98
     plethora
    0.95
     snippet
    0.94
    Activations Density 0.368%

    No Known Activations