© 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. 3-RES-JB
    11. 12188
    Prev
    Next
    INDEX
    Explanations

    the word "would"

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing hypothetical scenarios or desires

    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
    Cook
    -0.67
    rylic
    -0.66
    Pie
    -0.65
    isted
    -0.65
    æ³
    -0.65
    values
    -0.64
    resources
    -0.63
     Kag
    -0.63
    Reporting
    -0.62
    story
    -0.61
    POSITIVE LOGITS
     surely
    1.02
     doubtless
    0.98
     be
    0.98
     undoubtedly
    0.97
     inevitably
    0.94
     never
    0.92
     gladly
    0.90
     probably
    0.89
     invariably
    0.89
     suffice
    0.87
    Activations Density 0.160%

    No Known Activations