© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 19391
    Prev
    Next
    INDEX
    Explanations

    keywords related to events or instances of celebration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to celebrity culture and celebrations

    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
     deliveries
    -0.66
     containment
    -0.65
     guiActiveUnfocused
    -0.65
     handwriting
    -0.63
     improvement
    -0.59
    ĸļ
    -0.58
    WARD
    -0.58
     drafts
    -0.58
     operating
    -0.58
     adoption
    -0.58
    POSITIVE LOGITS
    brate
    1.29
    brates
    1.15
    ption
    1.05
    pter
    1.01
    Cele
    1.00
    vin
    0.96
    bs
    0.95
    cele
    0.95
    ptive
    0.95
    mony
    0.95
    Activations Density 0.016%

    No Known Activations