© 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. 6-RES-JB
    11. 11662
    Prev
    Next
    INDEX
    Explanations

    the word "Product" with varying degrees of specificity indicated by different activation values

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Product" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    laus
    -0.74
    trop
    -0.66
     Peninsula
    -0.66
    CLASSIFIED
    -0.66
    asons
    -0.65
    apo
    -0.65
     Brother
    -0.61
     Nights
    -0.61
     Electricity
    -0.61
     Shades
    -0.60
    POSITIVE LOGITS
    ivity
    1.41
    ively
    1.26
    ivities
    1.08
    iveness
    1.03
     packaging
    0.85
    Hunt
    0.81
    icons
    0.77
    rador
    0.76
    kit
    0.75
    ocratic
    0.75
    Activations Density 0.029%

    No Known Activations