© 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. 9-RES-JB
    11. 16446
    Prev
    Next
    INDEX
    Explanations

    phrases related to understanding and serious situations

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to comprehension and understanding of various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    boro
    -0.75
    hest
    -0.71
    inces
    -0.71
    gard
    -0.70
     favourites
    -0.69
    ottest
    -0.68
    idate
    -0.67
    rollers
    -0.67
    idates
    -0.67
    culosis
    -0.64
    POSITIVE LOGITS
     nuances
    1.18
    why
    1.16
     intric
    1.10
     dynamics
    1.07
     workings
    1.07
     WHY
    1.05
     complexities
    1.00
     rationale
    1.00
     context
    0.99
     meaning
    0.99
    Activations Density 0.299%

    No Known Activations