© 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. 11413
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names of companies or individuals

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial and economic changes

    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
    itual
    -0.70
     UID
    -0.68
     Ranking
    -0.58
    Pers
    -0.55
     Pers
    -0.54
     contradiction
    -0.54
    today
    -0.54
    izo
    -0.53
     Organizations
    -0.52
     Regarding
    -0.51
    POSITIVE LOGITS
     theirs
    1.25
     likewise
    1.04
     hers
    0.91
     thereafter
    0.79
    ģ«
    0.78
     nonexistent
    0.77
     unaffected
    0.73
     nowhere
    0.72
     accordingly
    0.72
     elsewhere
    0.72
    Activations Density 0.588%

    No Known Activations