© 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. 2-RES-JB
    11. 17742
    Prev
    Next
    INDEX
    Explanations

    words related to a specific name or topic, possibly related to a person named Lazarus.

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Lazarus" and its variations, along with related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Oslo
    -0.73
     Hawaiian
    -0.71
    ĨĴ
    -0.71
     Somali
    -0.71
    ãĥĥãĥĪ
    -0.70
    ãĥ¼ãĥ³
    -0.69
     Canterbury
    -0.69
    é¾
    -0.67
     Viking
    -0.67
    IZE
    -0.67
    POSITIVE LOGITS
     Laz
    1.01
    arus
    0.98
    hou
    0.94
    rael
    0.89
    uli
    0.86
    yp
    0.86
    ouri
    0.86
    arov
    0.86
    iness
    0.85
    igue
    0.83
    Activations Density 0.006%

    No Known Activations