© 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. 11-RES-JB
    11. 20741
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and military contexts

    oai_token-act-pair · gpt-3.5-turbo

    statements or opinions regarding a person's actions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whip
    -0.87
    XM
    -0.84
     pony
    -0.83
     Pence
    -0.83
     ponies
    -0.82
    ince
    -0.82
     Mississ
    -0.79
    anch
    -0.75
     Sha
    -0.75
     ho
    -0.74
    POSITIVE LOGITS
     Ber
    2.44
    Ber
    2.35
     Berger
    1.98
     Ger
    1.64
    Ger
    1.59
     Berg
    1.54
    Bern
    1.51
     Bern
    1.50
     ber
    1.31
     Bert
    1.30
    Activations Density 0.178%

    No Known Activations