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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 19656
    Prev
    Next
    INDEX
    Explanations

    words related to law, governance, and possibly politics

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to location or geographical features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.88
    etheless
    -0.87
    Compat
    -0.75
    maxwell
    -0.75
    Write
    -0.74
    Spoiler
    -0.74
    rawdownloadcloneembedreportprint
    -0.72
    WT
    -0.72
    DragonMagazine
    -0.70
    conserv
    -0.68
    POSITIVE LOGITS
    è
    0.76
    é
    0.74
    ê
    0.73
     Trop
    0.72
    ios
    0.71
    ogie
    0.69
     fem
    0.65
    bi
    0.65
    ét
    0.65
    endi
    0.64
    Activations Density 0.132%

    No Known Activations