© 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. 0-RES-JB
    11. 1211
    Prev
    Next
    INDEX
    Explanations

    words related to criticizing or expressing disapproval

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "ried," particularly in contexts relating to decision-making or determinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     requiring
    -0.66
     meaning
    -0.63
     upl
    -0.62
     Spartan
    -0.62
     interactive
    -0.59
     dot
    -0.58
     dots
    -0.58
     VIP
    -0.57
     providing
    -0.57
     Cascade
    -0.57
    POSITIVE LOGITS
    ried
    4.42
    rying
    2.65
    ries
    2.62
    riage
    1.83
    ry
    1.58
    risome
    1.46
    rier
    1.41
    riers
    1.38
    rys
    1.37
    rie
    1.28
    Activations Density 0.006%

    No Known Activations