© 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. 8-RES-JB
    11. 6791
    Prev
    Next
    INDEX
    Explanations

    words related to a specific named entity, "Dub"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Dub" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FTWARE
    -0.72
    ++++
    -0.70
    inventoryQuantity
    -0.70
    terday
    -0.70
     Newsp
    -0.70
    IDE
    -0.69
    andering
    -0.68
    IZE
    -0.67
     Snape
    -0.65
     actionGroup
    -0.65
    POSITIVE LOGITS
    step
    1.22
    bed
    1.19
    bing
    1.19
    ois
    1.14
    rov
    1.12
    bers
    1.00
    marine
    0.95
    bles
    0.93
    lish
    0.92
    plates
    0.91
    Activations Density 0.036%

    No Known Activations