© 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. 8346
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Ka" with a high degree of relevance

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named "Ka" or variations thereof

    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
    姫
    -1.00
    IONS
    -0.89
    ROR
    -0.84
    天
    -0.76
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.75
    cream
    -0.75
    OWER
    -0.74
    Ö¼
    -0.74
    ECT
    -0.73
    rawdownloadcloneembedreportprint
    -0.71
    POSITIVE LOGITS
     Ka
    1.02
    Ka
    0.96
    iser
    0.95
    isers
    0.92
    adian
    0.90
    iba
    0.89
    umat
    0.88
    pless
    0.84
    jac
    0.84
    TeX
    0.83
    Activations Density 0.010%

    No Known Activations