© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6057
    Prev
    Next
    INDEX
    Explanations

    words related to event celebration or occurrence

    oai_token-act-pair · gpt-3.5-turbo

    terms related to food and hospitality

    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
    soDeliveryDate
    -0.82
    izations
    -0.78
    ues
    -0.74
    omez
    -0.73
    izable
    -0.70
    olved
    -0.68
    chrom
    -0.68
     compuls
    -0.66
    inki
    -0.65
     socket
    -0.64
    POSITIVE LOGITS
    fare
    1.60
    nce
    0.90
    ments
    0.90
    lot
    0.88
    enance
    0.84
    rior
    0.83
     Fare
    0.82
    ttes
    0.81
    dn
    0.78
    rer
    0.74
    Activations Density 0.014%

    No Known Activations