© 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. 10425
    Prev
    Next
    INDEX
    Explanations

    instances where something is being added or increased

    oai_token-act-pair · gpt-3.5-turbo

    references to increases or additions

    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
    NING
    -0.67
    Bey
    -0.67
    ograms
    -0.67
    bane
    -0.66
     Zel
    -0.66
     WATCHED
    -0.65
     Gram
    -0.65
     Zimmer
    -0.63
    baum
    -0.62
     Nets
    -0.62
    POSITIVE LOGITS
    ictions
    1.07
    endum
    1.01
    itionally
    1.01
    itional
    1.00
     insult
    0.89
    icted
    0.86
    itious
    0.85
    itions
    0.83
    itivity
    0.82
    ition
    0.82
    Activations Density 0.044%

    No Known Activations