© 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. 8-RES-JB
    11. 1077
    Prev
    Next
    INDEX
    Explanations

    phrases related to well-wishing or blessings

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions that connect phrases or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HER
    -0.66
    uma
    -0.64
    ibble
    -0.63
    itans
    -0.62
    DX
    -0.62
    atten
    -0.62
    SPA
    -0.60
    Pub
    -0.60
    GREEN
    -0.59
    prim
    -0.57
    POSITIVE LOGITS
     thereby
    0.95
     thus
    0.95
     hence
    0.94
     consequently
    0.86
     therefore
    0.85
     furthermore
    0.84
     thereafter
    0.83
     vice
    0.82
     thence
    0.82
    rew
    0.81
    Activations Density 0.230%

    No Known Activations