© 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. 5418
    Prev
    Next
    INDEX
    Explanations

    specific instances or cases within a broader context

    oai_token-act-pair · gpt-3.5-turbo

    instances of inquiry or questioning about 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
    pires
    -0.92
    tains
    -0.85
     tries
    -0.83
    itates
    -0.82
     settles
    -0.82
     touches
    -0.80
     gathers
    -0.79
     helps
    -0.77
    Adds
    -0.76
     connects
    -0.76
    POSITIVE LOGITS
     are
    1.32
     ARE
    1.23
     aren
    1.22
    are
    1.12
    're
    1.10
    were
    1.03
    have
    1.01
     have
    1.00
     were
    1.00
     Are
    0.98
    Activations Density 1.061%

    No Known Activations