© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 18645
    Prev
    Next
    INDEX
    Explanations

    action-oriented instructions or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    suggestions or calls to action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dominates
    -0.61
    emale
    -0.60
    ariat
    -0.58
    omach
    -0.56
     wheelchair
    -0.54
    indle
    -0.52
     purported
    -0.52
    obs
    -0.52
    ovie
    -0.52
    DNA
    -0.52
    POSITIVE LOGITS
     yourself
    1.36
     yourselves
    1.23
     Yourself
    1.10
     wisely
    0.97
     your
    0.95
     carefully
    0.93
     preferably
    0.88
     sparing
    0.86
     ASAP
    0.84
    cknow
    0.81
    Activations Density 0.226%

    No Known Activations