Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 16969
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the name "Leon" with varying activations, potentially associated with Leon Trotsky or other individuals named Leon

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Leon" or related names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    skirts
    -0.71
    clips
    -0.69
    DIV
    -0.63
    glers
    -0.61
    STER
    -0.61
    ship
    -0.60
     à¨
    -0.59
     overrun
    -0.59
    ODUCT
    -0.59
    ifice
    -0.58
    POSITIVE LOGITS
    idas
    1.10
    ardo
    1.08
    hart
    0.98
    hardt
    0.89
     Trotsky
    0.88
    ora
    0.88
    idates
    0.84
    arious
    0.83
    hard
    0.83
    etti
    0.82
    Activations Density 0.027%

    No Known Activations