© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 6941
    Prev
    Next
    INDEX
    Explanations

    critiques related to product quality and value for money

    oai_token-act-pair · gpt-3.5-turbo

    evaluations of product quality and value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Coordinator
    -0.77
    Dialogue
    -0.74
    Zone
    -0.68
     Fenrir
    -0.67
    auldron
    -0.66
    LET
    -0.66
    wart
    -0.66
     circles
    -0.66
    ãĤ¼ãĤ¦ãĤ¹
    -0.64
     inhibition
    -0.64
    POSITIVE LOGITS
     priced
    1.63
     affordable
    1.55
     cheaper
    1.55
     cheap
    1.51
     pricey
    1.49
     cheaply
    1.47
     pric
    1.47
     inexpensive
    1.43
     expensive
    1.42
    priced
    1.38
    Activations Density 0.413%

    No Known Activations