© 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. 4-RES-JB
    11. 20844
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by a strong emotion or action verb

    oai_token-act-pair · gpt-3.5-turbo

    pronouns indicating personal involvement or reference in the text

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

    No Comments

    Negative Logits
     Kang
    -0.64
    ²¾
    -0.60
    ational
    -0.59
    upp
    -0.56
     Hold
    -0.55
     Tayyip
    -0.55
    Ŀ
    -0.54
    advertisement
    -0.54
     Kills
    -0.54
    ophobic
    -0.54
    POSITIVE LOGITS
     reasoned
    0.69
    added
    0.66
    instead
    0.62
    dos
    0.60
    dinand
    0.60
    bra
    0.59
     nevertheless
    0.59
    enei
    0.59
     heirs
    0.59
    uggest
    0.59
    Activations Density 0.504%

    No Known Activations