© 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. 15457
    Prev
    Next
    INDEX
    Explanations

    phrases related to small or insignificant details

    oai_token-act-pair · gpt-3.5-turbo

    mentions of small entities or concepts that emphasize importance in various contexts

    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
     Skies
    -0.79
    åĭ
    -0.69
     Roses
    -0.67
    andise
    -0.67
    hibited
    -0.66
    ukong
    -0.65
    ayn
    -0.65
     Gleaming
    -0.63
    aundering
    -0.60
    metics
    -0.58
    POSITIVE LOGITS
     (<
    1.32
     (~
    0.83
     insignificant
    0.82
     scattered
    0.80
    tiny
    0.80
     sized
    0.80
     niche
    0.79
     incremental
    0.78
     increments
    0.75
    Enlarge
    0.74
    Activations Density 0.358%

    No Known Activations