© 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. 1-RES-JB
    11. 20789
    Prev
    Next
    INDEX
    Explanations

    words related to the name 'Kua'

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the term "kua" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    displayText
    -0.68
    ticket
    -0.67
     CPS
    -0.65
    sharing
    -0.63
    spot
    -0.62
     Measures
    -0.62
    starter
    -0.60
    cube
    -0.59
    Catal
    -0.58
     Attribution
    -0.58
    POSITIVE LOGITS
    ua
    1.43
    ð
    0.98
    ascus
    0.91
    oa
    0.85
    UA
    0.85
    cci
    0.81
    awei
    0.81
    veland
    0.81
    veyard
    0.80
    zza
    0.79
    Activations Density 0.005%

    No Known Activations