© 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. 4-RES-JB
    11. 1041
    Prev
    Next
    INDEX
    Explanations

    dates written in a numerical format

    oai_token-act-pair · gpt-3.5-turbo

    numerical references related to dates

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

    No Comments

    Negative Logits
    igham
    -0.62
    igans
    -0.60
     hygiene
    -0.59
     bats
    -0.58
     CARD
    -0.56
     conver
    -0.56
     bin
    -0.53
     vector
    -0.53
    udeb
    -0.53
    ctors
    -0.52
    POSITIVE LOGITS
    th
    0.97
    rd
    0.89
    ths
    0.83
    stice
    0.79
    âĢ³
    0.75
    elt
    0.74
    EVA
    0.71
    TH
    0.70
    arten
    0.69
    CBC
    0.69
    Activations Density 0.079%

    No Known Activations