© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1698
    Prev
    Next
    INDEX
    Explanations

    prices expressed in a specific format (e.g., $X.XX)

    oai_token-act-pair · gpt-3.5-turbo

    references to prices, particularly those ending in '.99'

    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
    iqueness
    -0.77
    values
    -0.74
    igators
    -0.72
    otos
    -0.72
    umbn
    -0.71
    nesota
    -0.70
    population
    -0.65
    alist
    -0.64
    limits
    -0.64
    pty
    -0.63
    POSITIVE LOGITS
    /$
    1.07
    -$
    0.97
     USD
    0.90
    AU
    0.80
     cents
    0.75
    AUD
    0.73
    âĤ¬
    0.71
    ãģ¦
    0.71
     crore
    0.69
    chev
    0.67
    Activations Density 0.040%

    No Known Activations