© 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 EvalsExportsinterp-engineNEWAPI 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. 12222
    Prev
    Next
    INDEX
    Explanations

    mention of news organizations and reported events

    oai_token-act-pair · gpt-3.5-turbo

    references to media organizations and their reporting activities

    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
     unlocking
    -0.79
     unlocked
    -0.75
     Awakening
    -0.70
     exerc
    -0.69
     unlock
    -0.69
    tec
    -0.68
    gui
    -0.68
     concrete
    -0.68
     achievable
    -0.68
     Solitaire
    -0.67
    POSITIVE LOGITS
     editorial
    1.23
    reporting
    1.14
     reporting
    1.09
     journalistic
    1.07
     headline
    1.04
     publishes
    1.02
     Reporting
    1.01
     airing
    1.01
     sensational
    1.00
     publish
    1.00
    Activations Density 0.796%

    No Known Activations