© 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. 17079
    Prev
    Next
    INDEX
    Explanations

    personal names within historical contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to historical figures, events, or the context of their actions

    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
     Recession
    -0.77
    Sorry
    -0.73
     selfies
    -0.70
    Looks
    -0.69
     Thumbnails
    -0.69
    âĶģ
    -0.67
     Adds
    -0.67
     WATCH
    -0.67
     aren
    -0.66
     moms
    -0.66
    POSITIVE LOGITS
     undertook
    1.35
     proceeded
    1.31
     persuaded
    1.23
     commenced
    1.16
     remarked
    1.16
     accompanied
    1.16
     endeav
    1.16
     succeeded
    1.15
     instructed
    1.14
     volunteered
    1.13
    Activations Density 0.378%

    No Known Activations