© 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. 1-RES-JB
    11. 14258
    Prev
    Next
    INDEX
    Explanations

    dates related to athletic events or schedules

    oai_token-act-pair · gpt-3.5-turbo

    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 @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SpaceEngineers
    -0.78
    ultane
    -0.72
    adish
    -0.71
    ollen
    -0.71
    aryl
    -0.71
    unc
    -0.69
    ulner
    -0.69
    bb
    -0.67
     Auditor
    -0.67
    cffff
    -0.67
    POSITIVE LOGITS
     princ
    0.67
     polyg
    0.67
     behalf
    0.66
     lett
    0.66
    FUL
    0.65
     shalt
    0.64
     checkout
    0.64
     visitation
    0.64
    ting
    0.61
     fluoride
    0.59
    Activations Density 0.000%

    No Known Activations