© 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. 4487
    Prev
    Next
    INDEX
    Explanations

    mentions related to sports victories and achievements

    oai_token-act-pair · gpt-3.5-turbo
    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
     Emails
    -0.93
     censored
    -0.77
    FBI
    -0.71
    cens
    -0.71
    OSED
    -0.71
     intrusive
    -0.70
    bugs
    -0.70
     Harm
    -0.68
     responsive
    -0.68
     nudity
    -0.67
    POSITIVE LOGITS
     accol
    1.39
     accomplishment
    1.32
     trophy
    1.26
     trophies
    1.22
     unbeaten
    1.20
     bragging
    1.18
     achievement
    1.16
     glory
    1.15
     feat
    1.14
     feats
    1.13
    Activations Density 0.575%

    No Known Activations