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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 22313
    Prev
    Next
    INDEX
    Explanations

    filament-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to filtering and classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONES
    -0.81
    FUL
    -0.74
     Lans
    -0.70
    EEK
    -0.67
     Bread
    -0.67
    é¾įå
    -0.66
    izu
    -0.66
     Pax
    -0.63
     Leap
    -0.63
     Baldwin
    -0.62
    POSITIVE LOGITS
     fil
    1.05
    clud
    0.91
    ilies
    0.90
    teenth
    0.89
    ulators
    0.88
    ials
    0.86
    uity
    0.84
    bage
    0.83
    umbers
    0.82
    gins
    0.81
    Activations Density 0.008%

    No Known Activations