Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 9012
    Prev
    Next
    INDEX
    Explanations

    technical terms or abbreviations related to energy and medicine, particularly those starting with the letter 'E'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'E'

    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
     rang
    -0.61
     hitting
    -0.60
     hamm
    -0.60
     sund
    -0.59
     mashed
    -0.59
     summons
    -0.58
     paternity
    -0.57
     unpaid
    -0.57
     once
    -0.57
     insurance
    -0.56
    POSITIVE LOGITS
    E
    3.51
    Es
    2.06
    EB
    1.90
    EF
    1.74
    EH
    1.71
     E
    1.68
    e
    1.60
    EY
    1.56
    EA
    1.55
    EE
    1.49
    Activations Density 0.028%

    No Known Activations