© 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. 6-RES-JB
    11. 16653
    Prev
    Next
    INDEX
    Explanations

    phrases related to progression or advancement

    oai_token-act-pair · gpt-3.5-turbo

    phrases referencing sequential actions or steps

    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
    lys
    -0.77
    asted
    -0.75
    olls
    -0.72
    itable
    -0.68
     Sins
    -0.68
     sweats
    -0.68
    enced
    -0.66
     Sapp
    -0.64
    BW
    -0.63
    ographies
    -0.63
    POSITIVE LOGITS
    phase
    0.78
     Steps
    0.73
    ablishment
    0.73
    aphael
    0.73
     step
    0.73
     refinement
    0.72
    step
    0.71
     Investigations
    0.71
     toward
    0.70
     awaits
    0.69
    Activations Density 0.051%

    No Known Activations