© 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. 12067
    Prev
    Next
    INDEX
    Explanations

    nouns related to politics and world events

    oai_token-act-pair · gpt-3.5-turbo

    conjunctive phrases that connect multiple subjects or ideas

    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
    scribe
    -0.83
    igm
    -0.72
    »Ĵ
    -0.72
    agues
    -0.70
    quer
    -0.70
    agos
    -0.69
    atech
    -0.69
    uese
    -0.67
    ãĤ¹ãĥĪ
    -0.67
    lear
    -0.66
    POSITIVE LOGITS
     lack
    1.47
     inability
    1.42
     unwillingness
    1.39
     consequ
    1.32
     resultant
    1.26
     refusal
    1.25
     reluctance
    1.24
     inadequate
    1.22
     subsequent
    1.19
     inaction
    1.17
    Activations Density 0.306%

    No Known Activations