© 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. 12-RES-JB
    11. 2973
    Prev
    Next
    INDEX
    Explanations

    adjectives and nouns related to silence, certainty, and quietness

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    concepts and references to silence, quietness, and related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Drawn
    -0.68
     Flex
    -0.60
    lete
    -0.57
    rig
    -0.57
     Equip
    -0.57
    Ax
    -0.56
    hyd
    -0.55
    sych
    -0.54
     Balance
    -0.54
    ALD
    -0.54
    POSITIVE LOGITS
     achie
    0.81
    ifference
    0.77
    edom
    0.73
     acquies
    0.72
    ariat
    0.70
    atorium
    0.70
    gren
    0.70
    ower
    0.70
     contemplation
    0.69
    quished
    0.66
    Activations Density 0.058%

    No Known Activations