© 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. 4-RES-JB
    11. 6972
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something is used or done solely by one person, group, or category

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "exclusively."

    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
    enegger
    -0.81
    former
    -0.74
    SCP
    -0.71
     Millennium
    -0.70
    akeru
    -0.69
    ulz
    -0.67
    Afee
    -0.65
    ocene
    -0.64
    dfx
    -0.64
    leaders
    -0.64
    POSITIVE LOGITS
     exclusively
    0.93
     geared
    0.83
     bred
    0.79
     focused
    0.79
     owned
    0.77
     revolves
    0.76
     tailored
    0.74
     resides
    0.74
     screened
    0.73
     marketed
    0.73
    Activations Density 0.011%

    No Known Activations