© 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. 10263
    Prev
    Next
    INDEX
    Explanations

    specific instances of actions or descriptions of actions

    oai_token-act-pair · gpt-3.5-turbo

    interrogative phrases or words indicating questioning or making inquiries

    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
    }}}
    -0.52
     WARNING
    -0.51
     VIDEOS
    -0.51
    tro
    -0.47
    ))))
    -0.46
     Instructions
    -0.46
     dwindling
    -0.45
    tnc
    -0.45
    ovember
    -0.45
     unanswered
    -0.44
    POSITIVE LOGITS
     they
    1.36
     she
    1.29
     he
    1.28
    they
    1.19
    she
    1.04
     THEY
    0.95
     we
    0.91
     SHE
    0.90
    he
    0.85
    They
    0.82
    Activations Density 0.657%

    No Known Activations