© 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. 11-RES-JB
    11. 22591
    Prev
    Next
    INDEX
    Explanations

    entities or individuals who did not respond to requests for comments or information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "respond" in various contexts

    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
    é¾įå
    -0.73
    dar
    -0.70
    ¬¼
    -0.63
    iculture
    -0.62
    igi
    -0.61
    rider
    -0.61
    mingham
    -0.59
    chin
    -0.58
    ETF
    -0.57
    rities
    -0.55
    POSITIVE LOGITS
     favorably
    1.01
     promptly
    1.00
     positively
    0.98
     to
    0.94
     thereto
    0.91
     directly
    0.88
     affirm
    0.88
     angrily
    0.88
     satisf
    0.85
     forcefully
    0.84
    Activations Density 0.046%

    No Known Activations