© 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. 17159
    Prev
    Next
    INDEX
    Explanations

    words related to understanding, realization, and implications

    oai_token-act-pair · gpt-3.5-turbo

    references to understanding and awareness in various contexts

    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
    icides
    -0.77
    reau
    -0.74
    exclusive
    -0.74
     roundup
    -0.73
    icide
    -0.68
    aunder
    -0.68
    odder
    -0.65
    agne
    -0.64
    olphins
    -0.63
    ahan
    -0.63
    POSITIVE LOGITS
     limitations
    0.78
     firsthand
    0.74
     predicament
    0.73
     nuances
    0.73
    Privacy
    0.70
     plight
    0.70
    atorium
    0.69
     similarities
    0.68
    ELF
    0.68
    concept
    0.68
    Activations Density 0.239%

    No Known Activations