© 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. 6-RES-JB
    11. 7975
    Prev
    Next
    INDEX
    Explanations

    names with the pattern "Wald", "Vald", and "Mald" in the text

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names related to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hift
    -0.79
    itance
    -0.75
    BILITY
    -0.71
    ITE
    -0.70
    HER
    -0.68
     Occupations
    -0.67
    Cs
    -0.67
    RT
    -0.64
     inflamm
    -0.64
    ptive
    -0.63
    POSITIVE LOGITS
    stad
    0.94
    ©¶æ¥µ
    0.87
    ress
    0.86
    »Ĵ
    0.85
    orf
    0.85
    ric
    0.83
    ivia
    0.83
     Wald
    0.82
    anza
    0.81
    rey
    0.79
    Activations Density 0.035%

    No Known Activations