© 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. 3-RES-JB
    11. 15351
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating a strong likelihood or obligation towards a certain outcome

    oai_token-act-pair · gpt-3.5-turbo

    the word "bound" and its variations, indicating obligations or connections

    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
    omi
    -0.70
     fielded
    -0.70
    issance
    -0.69
    ciation
    -0.67
    soDeliveryDate
    -0.67
    STEM
    -0.65
    sych
    -0.64
    otrop
    -0.63
    ETHOD
    -0.63
    elli
    -0.61
    POSITIVE LOGITS
     bound
    1.01
    ridges
    0.92
    binding
    0.88
    fold
    0.84
    bound
    0.84
    unin
    0.77
    lessly
    0.77
    eering
    0.74
    gling
    0.74
    uckland
    0.73
    Activations Density 0.013%

    No Known Activations