© 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. 11-RES-JB
    11. 7444
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals and their actions

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs indicating actions or statements made by individuals

    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
    bery
    -0.72
    uce
    -0.68
    eem
    -0.68
    hack
    -0.68
    umping
    -0.64
    jam
    -0.63
    rush
    -0.62
     strand
    -0.60
     Might
    -0.60
    bush
    -0.59
    POSITIVE LOGITS
     consulted
    1.20
     spoken
    1.12
     received
    1.09
     heard
    1.04
     listened
    1.00
     contacted
    1.00
     been
    1.00
     begun
    0.99
     doubts
    0.99
     reviewed
    0.97
    Activations Density 0.182%

    No Known Activations