© 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. 22109
    Prev
    Next
    INDEX
    Explanations

    phrases related to reflective statements or conclusions

    oai_token-act-pair · gpt-3.5-turbo

    the recurring phrase "at the end of the day."

    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
     Theresa
    -0.77
     Plum
    -0.67
     Carney
    -0.66
     Barcl
    -0.66
     Harrington
    -0.66
    kinson
    -0.64
     Regulation
    -0.64
    worthy
    -0.64
     Families
    -0.63
     Krug
    -0.62
    POSITIVE LOGITS
    OOK
    0.83
    spection
    0.71
    BuyableInstoreAndOnline
    0.68
    AAF
    0.66
     poker
    0.65
     suspic
    0.64
     corrid
    0.64
     saline
    0.64
     exploration
    0.63
     methamphetamine
    0.61
    Activations Density 0.196%

    No Known Activations