© 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. 6326
    Prev
    Next
    INDEX
    Explanations

    mentions of age and time in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific ages and corresponding times

    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
    Iterator
    -0.68
    film
    -0.63
    HTTP
    -0.62
    Shell
    -0.59
    Russ
    -0.59
    PLA
    -0.58
    ername
    -0.58
    arch
    -0.57
    washed
    -0.57
    gravity
    -0.57
    POSITIVE LOGITS
     least
    1.01
    abase
    0.96
    roph
    0.92
    yp
    0.88
    olls
    0.85
    rium
    0.83
     birth
    0.82
     odds
    0.81
     conception
    0.78
     times
    0.78
    Activations Density 0.171%

    No Known Activations