© 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. 9634
    Prev
    Next
    INDEX
    Explanations

    phrases indicating difficulty or challenges

    oai_token-act-pair · gpt-3.5-turbo
    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
    Sport
    -0.74
    ement
    -0.73
    umes
    -0.73
    iture
    -0.64
    ui
    -0.64
    emouth
    -0.64
    irie
    -0.64
    ItemImage
    -0.63
    nette
    -0.63
    ritz
    -0.63
    POSITIVE LOGITS
     adjusting
    0.99
     navigating
    0.97
     locating
    0.96
     reconcil
    0.94
     distinguishing
    0.94
     finding
    0.92
     getting
    0.92
     adapting
    0.91
     figuring
    0.91
     interpreting
    0.91
    Activations Density 0.070%

    No Known Activations