© 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. 24260
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a high likelihood or possibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating likelihood or uncertainty

    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
    anted
    -0.61
     Sunshine
    -0.61
     Avalon
    -0.60
    anon
    -0.59
    alez
    -0.58
     Bahá
    -0.58
     Portal
    -0.57
    oko
    -0.57
    risome
    -0.57
     Sunset
    -0.57
    POSITIVE LOGITS
     be
    0.81
    ŃĶ
    0.80
     msec
    0.79
    LECT
    0.77
     afford
    0.76
    ect
    0.75
     satisfy
    0.70
     suffice
    0.70
    idate
    0.69
    hap
    0.69
    Activations Density 0.034%

    No Known Activations