© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 16367
    Prev
    Next
    INDEX
    Explanations

    the name "Ron"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Ron" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.71
    ailable
    -0.69
     canvas
    -0.66
    TAG
    -0.65
    kaya
    -0.65
     judgments
    -0.64
    idas
    -0.64
    soever
    -0.63
     disposal
    -0.62
    Loader
    -0.62
    POSITIVE LOGITS
     Ron
    3.60
    Ron
    2.72
     Ronald
    1.80
     Ronnie
    1.65
     Hermione
    1.47
     Ginny
    1.46
     Rand
    1.30
    RON
    1.29
     Russ
    1.28
     Paul
    1.27
    Activations Density 0.020%

    No Known Activations