© 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. 3-RES-JB
    11. 20443
    Prev
    Next
    INDEX
    Explanations

    phrases related to survey results or statistics

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or places

    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
    inka
    -0.74
    iddling
    -0.74
    hop
    -0.73
     casc
    -0.72
    onomy
    -0.70
    gorith
    -0.68
    oen
    -0.66
    sha
    -0.66
    otive
    -0.66
    orph
    -0.66
    POSITIVE LOGITS
    Gallery
    0.76
    quartered
    0.76
    esson
    0.72
    warm
    0.65
     sleeps
    0.64
    bats
    0.63
    SOURCE
    0.62
     athlet
    0.61
     ARTICLE
    0.60
     Milan
    0.60
    Activations Density 0.000%

    No Known Activations