© 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. 2201
    Prev
    Next
    INDEX
    Explanations

    actions or instructions directed at the reader

    oai_token-act-pair · gpt-3.5-turbo

    references to the second person ("you") in various contexts

    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
    interstitial
    -0.83
    Reviewer
    -0.74
    Georg
    -0.71
    Contents
    -0.68
    Beer
    -0.67
    Gene
    -0.61
    Balt
    -0.61
    former
    -0.60
    ogue
    -0.59
    HCR
    -0.59
    POSITIVE LOGITS
    're
    1.38
     intend
    1.20
     decide
    1.19
     want
    1.16
     accidentally
    1.09
     aren
    1.09
     choose
    1.09
     omit
    1.08
     prefer
    1.06
    've
    1.06
    Activations Density 0.108%

    No Known Activations