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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 12885
    Prev
    Next
    INDEX
    Explanations

    words related to awe and wonder

    oai_token-act-pair · gpt-3.5-turbo

    words related to positive qualities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Finder
    -0.67
     Rite
    -0.66
     Antar
    -0.63
     Jihad
    -0.62
     Moroc
    -0.62
     Scand
    -0.61
     Jav
    -0.60
     Ry
    -0.59
    £ı
    -0.58
     tert
    -0.58
    POSITIVE LOGITS
    ened
    1.18
    ledged
    1.15
    oming
    1.02
    enment
    0.99
    ledge
    0.95
    ruck
    0.89
    ening
    0.87
    LED
    0.86
    omen
    0.85
    aken
    0.85
    Activations Density 0.084%

    No Known Activations