© 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. 3-RES-JB
    11. 20456
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or incidents, such as criminal activities or organizational support

    oai_token-act-pair · gpt-3.5-turbo

    words related to cancellations or medical terms associated with health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cheong
    -0.67
    ¯
    -0.60
    tip
    -0.59
     sow
    -0.58
     Yen
    -0.55
    dk
    -0.55
    ensional
    -0.55
    isites
    -0.54
     pint
    -0.53
    yden
    -0.53
    POSITIVE LOGITS
    ulhu
    0.98
    ãĤ¼ãĤ¦ãĤ¹
    0.81
    ãĥĥãĥī
    0.77
    rera
    0.74
    berus
    0.73
    pillar
    0.71
     Unch
    0.67
    ito
    0.67
    illion
    0.65
    illo
    0.64
    Activations Density 0.094%

    No Known Activations