© 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. 7-RES-JB
    11. 18637
    Prev
    Next
    INDEX
    Explanations

    text related to variations or different forms of something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to variations and variants in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lins
    -0.86
    ħĭ
    -0.83
    lehem
    -0.77
    ported
    -0.72
    Ķ
    -0.70
    yers
    -0.68
    runner
    -0.68
    ת
    -0.68
    İ
    -0.67
    ij
    -0.67
    POSITIVE LOGITS
     thereof
    0.98
    arily
    0.91
     Vari
    0.79
     allele
    0.78
    arios
    0.74
    dayName
    0.71
     spelling
    0.70
     variants
    0.69
    aution
    0.68
    pmwiki
    0.67
    Activations Density 0.056%

    No Known Activations