© 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. 19691
    Prev
    Next
    INDEX
    Explanations

    dates and events

    oai_token-act-pair · gpt-3.5-turbo

    references to specific timelines or events related to actions and locations

    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
    #$
    -0.47
    oeuv
    -0.47
    poon
    -0.47
    planet
    -0.46
    edly
    -0.46
     (&
    -0.44
    annah
    -0.44
    ridges
    -0.43
    Oregon
    -0.43
     Spoiler
    -0.43
    POSITIVE LOGITS
    iatrics
    0.51
     fructose
    0.45
    giene
    0.44
    ikers
    0.44
    umbing
    0.42
     ECB
    0.42
    EMBER
    0.42
     Jude
    0.41
     Carbuncle
    0.41
    idges
    0.41
    Activations Density 1.674%

    No Known Activations