© 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. 6-RES-JB
    11. 9163
    Prev
    Next
    INDEX
    Explanations

    phrases indicating various levels of desirability or importance

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing opinions or judgments about various situations or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acca
    -0.66
    onut
    -0.63
     dramas
    -0.60
    ership
    -0.60
    plates
    -0.59
    illa
    -0.57
    internal
    -0.57
    pread
    -0.56
    olulu
    -0.55
    opus
    -0.54
    POSITIVE LOGITS
     TAMADRA
    0.70
    natureconservancy
    0.68
     sooner
    0.66
    acted
    0.65
     feas
    0.65
    role
    0.64
     someday
    0.62
    SPONSORED
    0.62
    unic
    0.61
    keyes
    0.61
    Activations Density 0.328%

    No Known Activations