© 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. 17234
    Prev
    Next
    INDEX
    Explanations

    phrases related to proposing or seeking solutions to problems or challenges

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the concept of "solution" or approaches to problems

    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
    horn
    -0.72
    *)
    -0.69
    ports
    -0.66
    rings
    -0.65
    boxing
    -0.62
    ndra
    -0.62
    estial
    -0.61
    tun
    -0.61
    CI
    -0.60
    bah
    -0.59
    POSITIVE LOGITS
     overcome
    1.02
     avoid
    0.94
     counteract
    0.94
     ensure
    0.93
     solve
    0.89
    iling
    0.88
     maximize
    0.86
     accompany
    0.85
     satisfy
    0.85
     achieve
    0.85
    Activations Density 0.185%

    No Known Activations