© 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. 1620
    Prev
    Next
    INDEX
    Explanations

    phrases expressing value or importance

    oai_token-act-pair · gpt-3.5-turbo

    instances of something being described as valuable or worth pursuing

    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
     Hilbert
    -0.75
    gdala
    -0.69
     Edison
    -0.65
     Frazier
    -0.65
    oslov
    -0.65
    Marie
    -0.61
     Frontier
    -0.61
     VIDEOS
    -0.61
     Graphics
    -0.60
     Townsend
    -0.60
    POSITIVE LOGITS
     consideration
    0.92
    folios
    0.85
     mentioning
    0.83
    keeping
    0.79
     careful
    0.79
     noting
    0.77
    iness
    0.77
     remembering
    0.75
    ily
    0.75
    ighed
    0.73
    Activations Density 0.028%

    No Known Activations