© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 18198
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to computer software and systems

    oai_token-act-pair · gpt-3.5-turbo

    terms related to performance and functionality in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    certain words following "and"

    Explanation Uploaded by User
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •L9 resid features following 'and'

    No Comments

    Negative Logits
    pload
    -0.75
    eday
    -0.69
    bda
    -0.68
    renheit
    -0.68
    tk
    -0.64
    lier
    -0.59
    anamo
    -0.59
    sylv
    -0.59
    azo
    -0.57
    bledon
    -0.57
    POSITIVE LOGITS
     alike
    1.36
     respectively
    1.21
     collide
    0.88
     are
    0.78
    ¶
    0.71
     combine
    0.71
    ↵↵
    0.70
     unite
    0.69
     perspectives
    0.67
     aren
    0.66
    Activations Density 0.438%

    No Known Activations