© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19350
    Prev
    Next
    INDEX
    Explanations

    phrases related to advantages or benefits

    oai_token-act-pair · gpt-3.5-turbo

    terms related to benefits, features, and challenges associated with various subjects

    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
    psc
    -0.81
    aq
    -0.65
    ceans
    -0.65
     Tsukuyomi
    -0.63
    eric
    -0.63
    minent
    -0.61
    raph
    -0.60
    Date
    -0.60
     Essex
    -0.59
    onics
    -0.58
    POSITIVE LOGITS
     overlooked
    0.77
     relates
    0.76
     recurring
    0.74
    factor
    0.72
     pecul
    0.69
     encouraged
    0.66
     distinguishing
    0.65
     drawback
    0.65
     distinguishes
    0.64
     contrad
    0.64
    Activations Density 0.189%

    No Known Activations