© 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. 4-RES-JB
    11. 22277
    Prev
    Next
    INDEX
    Explanations

    phrases related to someone's experience or activities in a specific time period

    oai_token-act-pair · gpt-3.5-turbo

    references to periods of time

    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
     oneself
    -0.70
     ourselves
    -0.66
     yourselves
    -0.64
    arth
    -0.62
     Vish
    -0.61
    gru
    -0.61
    AIN
    -0.60
     yourself
    -0.60
     Kell
    -0.59
     tide
    -0.58
    POSITIVE LOGITS
    mates
    1.00
     counterparts
    0.81
     mates
    0.80
     peers
    0.77
    liest
    0.75
    favorite
    0.74
     predecessors
    0.73
     certs
    0.72
     brethren
    0.72
    pan
    0.72
    Activations Density 0.112%

    No Known Activations