© 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. 6285
    Prev
    Next
    INDEX
    Explanations

    time-related references in years

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "years" in a temporal context

    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
    edIn
    -0.71
     redes
    -0.67
    actionDate
    -0.62
    Mat
    -0.62
    Values
    -0.60
    emort
    -0.59
     Pengu
    -0.59
    hod
    -0.59
    ference
    -0.59
    Sav
    -0.57
    POSITIVE LOGITS
    -'
    0.82
    âĢ²
    0.80
     onwards
    0.74
     olds
    0.73
    ional
    0.71
     onward
    0.66
    rees
    0.65
    SPONSORED
    0.65
    frames
    0.65
    .?
    0.63
    Activations Density 0.083%

    No Known Activations