© 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. 3-RES-JB
    6. 11415
    Prev
    Next
    INDEX
    Explanations

    lingo related to raising the stakes or increasing the intensity of a situation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to increasing stakes or challenges, particularly in competitive or serious contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DS
    -0.75
    ively
    -0.75
    ockey
    -0.71
    HM
    -0.69
    ieve
    -0.67
    ooters
    -0.65
     crown
    -0.63
     Cohn
    -0.63
    VS
    -0.63
    ienne
    -0.62
    POSITIVE LOGITS
    galitarian
    0.90
    holes
    0.89
     ante
    0.87
     complication
    0.73
    zee
    0.71
    ktop
    0.68
    verages
    0.67
    hole
    0.67
     gobl
    0.67
    avery
    0.66
    Activations Density 0.028%

    No Known Activations