© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 20595
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "second" with various contexts and variations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "second"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roots
    -0.75
    Cache
    -0.74
    Statistics
    -0.72
    ETS
    -0.68
    Paper
    -0.68
    restling
    -0.68
    åİ
    -0.66
    IGHTS
    -0.66
    ãĤĭ
    -0.65
    EXT
    -0.65
    POSITIVE LOGITS
     baseman
    1.19
    arily
    0.98
    hand
    0.89
    assian
    0.83
     consecutive
    0.81
     cousin
    0.81
     successive
    0.79
     wave
    0.76
    endment
    0.76
     installment
    0.76
    Activations Density 0.041%

    No Known Activations