© 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 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. 10-RES-JB
    11. 4551
    Prev
    Next
    INDEX
    Explanations

    specific days of events

    oai_token-act-pair · gpt-3.5-turbo

    references to specific days and nights within a timeline

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.85
    olate
    -0.72
    iability
    -0.69
    ategor
    -0.66
    ictive
    -0.65
    ãĤ¤ãĥĪ
    -0.65
    itic
    -0.64
    Location
    -0.64
     Flavoring
    -0.62
    Interstitial
    -0.62
    POSITIVE LOGITS
     before
    1.00
     BEFORE
    0.82
     preceding
    0.81
     beforehand
    0.76
     prior
    0.76
     they
    0.71
     after
    0.69
     of
    0.68
    before
    0.67
    lights
    0.67
    Activations Density 0.066%

    No Known Activations