© 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
    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. 2971
    Prev
    Next
    INDEX
    Explanations

    words related to authority, power dynamics, and legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    important actions or consequences related to events, particularly in political or social contexts

    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
     Revision
    -0.64
     postwar
    -0.63
     Kush
    -0.62
     1948
    -0.61
     1906
    -0.59
     notwithstanding
    -0.59
     Crunch
    -0.59
     Alley
    -0.58
     Huff
    -0.58
     Ballard
    -0.58
    POSITIVE LOGITS
    tnc
    0.84
    DCS
    0.81
    ]);
    0.78
    >]
    0.76
    aeus
    0.75
    Reviewer
    0.75
    taboola
    0.75
    erd
    0.72
    ');
    0.72
    >>>>
    0.69
    Activations Density 0.569%

    No Known Activations