© 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. 10-RES-JB
    11. 8577
    Prev
    Next
    INDEX
    Explanations

    years or specific dates

    oai_token-act-pair · gpt-3.5-turbo

    specific years and dates mentioned in the text

    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
    OSH
    -0.80
    ©¶æ
    -0.76
    ographed
    -0.64
     assisted
    -0.61
    ioch
    -0.60
     ¶
    -0.60
     hereditary
    -0.60
    ablished
    -0.59
    license
    -0.59
    este
    -0.58
    POSITIVE LOGITS
     onwards
    1.02
    âĢ²
    0.99
     onward
    0.89
     looms
    0.82
    terms
    0.82
     marks
    0.80
    ivably
    0.74
     promises
    0.74
    å¹
    0.72
     festivities
    0.72
    Activations Density 0.188%

    No Known Activations