© 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. 10-RES-JB
    11. 5821
    Prev
    Next
    INDEX
    Explanations

    people's names, specifically looking for one name containing the letter "J" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of people or organizations

    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
    baugh
    -0.81
    enegger
    -0.76
    anamo
    -0.68
    redients
    -0.67
    shaw
    -0.66
    ebted
    -0.66
    ancies
    -0.66
    advertisement
    -0.64
    rador
    -0.63
    Äĩ
    -0.63
    POSITIVE LOGITS
    DF
    1.07
    NP
    1.07
    CE
    1.03
    NW
    1.01
    LC
    1.01
    VO
    1.00
    BS
    0.99
    IB
    0.99
    PL
    0.98
    NY
    0.98
    Activations Density 0.066%

    No Known Activations