© 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. 13514
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific text formatting or software function

    oai_token-act-pair · gpt-3.5-turbo

    references to specific products or brands related to makeup and theater-related terms

    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
    ICLE
    -0.81
    uers
    -0.80
    UE
    -0.80
    ues
    -0.80
    mary
    -0.79
    lon
    -0.77
    INTON
    -0.75
    keeper
    -0.72
    DNA
    -0.72
    metic
    -0.71
    POSITIVE LOGITS
    emort
    0.90
     sized
    0.84
    ocular
    0.82
     sandwiches
    0.81
     parach
    0.75
    ipolar
    0.75
     shrimp
    0.74
     bom
    0.73
    agascar
    0.72
     parachute
    0.72
    Activations Density 0.019%

    No Known Activations