© 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. 2-RES-JB
    11. 1049
    Prev
    Next
    INDEX
    Explanations

    the word "mulling" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to contemplation or deep thinking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cious
    -0.73
    REM
    -0.69
    È
    -0.65
    Grant
    -0.63
     Sector
    -0.61
     IMAGES
    -0.60
     afore
    -0.60
    Merit
    -0.60
    UU
    -0.59
    Newsletter
    -0.58
    POSITIVE LOGITS
     mull
    1.24
    igans
    1.07
    igan
    1.02
    uten
    0.97
    istani
    0.96
    aroo
    0.94
    ipedia
    0.87
    ahs
    0.87
    abouts
    0.86
    igating
    0.86
    Activations Density 0.004%

    No Known Activations