© 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. 8-RES-JB
    11. 3436
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Sideline"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Sid

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andise
    -0.77
     Doomsday
    -0.71
    naire
    -0.70
    anwhile
    -0.67
    growth
    -0.64
    ãģ£
    -0.61
    MQ
    -0.60
     UNESCO
    -0.59
    ment
    -0.58
     Seraph
    -0.57
    POSITIVE LOGITS
    eways
    1.35
    etr
    1.18
    iple
    0.90
    ouble
    0.89
    eless
    0.87
     Meier
    0.85
    este
    0.85
    emy
    0.83
    eway
    0.82
    itional
    0.82
    Activations Density 0.045%

    No Known Activations