© 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. 6809
    Prev
    Next
    INDEX
    Explanations

    words related to importance or necessity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "essential" and related contexts

    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
     huh
    -0.75
    walk
    -0.68
     Scores
    -0.67
     Gets
    -0.66
    scape
    -0.66
     Hmm
    -0.63
    bows
    -0.63
     Shoot
    -0.63
    vette
    -0.63
    oping
    -0.61
    POSITIVE LOGITS
     essential
    3.35
    essential
    2.43
     indispensable
    2.34
     Essential
    2.25
     essentials
    2.16
     vital
    2.13
     crucial
    1.95
     necessary
    1.73
     invaluable
    1.72
     important
    1.68
    Activations Density 0.012%

    No Known Activations