© 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. 23989
    Prev
    Next
    INDEX
    Explanations

    dates or instances when events or activities took place

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "held."

    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
    ICO
    -0.61
    Reward
    -0.60
     Loading
    -0.58
     Translation
    -0.56
    tro
    -0.54
     Horde
    -0.54
    )))
    -0.54
    ļéĨĴ
    -0.53
    Drive
    -0.52
    WARD
    -0.52
    POSITIVE LOGITS
     annually
    1.21
     jointly
    1.13
     outdoors
    1.12
     concurrently
    1.04
     consecut
    1.01
     quarterly
    0.95
     indoors
    0.94
     monthly
    0.92
     simultaneously
    0.90
     yearly
    0.88
    Activations Density 0.134%

    No Known Activations