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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 7209
    Prev
    Next
    INDEX
    Explanations

    mention of specific groups or entities, such as "Kraken," "YPG," "Firefly," "Flake," or "Zoe."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific groups, events, or substances related to conflict and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nel
    -0.83
    advert
    -0.82
    icip
    -0.78
    alities
    -0.77
    aneously
    -0.76
    aud
    -0.74
    bed
    -0.73
     Isaiah
    -0.72
    ibur
    -0.71
    icides
    -0.70
    POSITIVE LOGITS
     Unicorn
    0.78
     Rossi
    0.74
    ¬¼
    0.73
     CoC
    0.68
    ritch
    0.67
     Dice
    0.67
    VOL
    0.65
    Ń·
    0.65
     Commodore
    0.64
     Rampage
    0.63
    Activations Density 0.022%

    No Known Activations