© 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. 8-RES-JB
    11. 20443
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something will last a long time or indefinitely

    oai_token-act-pair · gpt-3.5-turbo

    the concept of permanence or lasting impact

    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
    anooga
    -1.00
     Cosponsors
    -1.00
    annis
    -0.88
    Cu
    -0.84
    rera
    -0.71
    sonian
    -0.69
    ioch
    -0.69
    DragonMagazine
    -0.68
    acist
    -0.67
    aspx
    -0.67
    POSITIVE LOGITS
    more
    1.03
    lasting
    0.96
     ago
    0.87
    green
    0.85
    ãĤ£
    0.79
     thereafter
    0.78
     å¤
    0.72
    changed
    0.71
    forth
    0.69
    lane
    0.67
    Activations Density 0.026%

    No Known Activations