© 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. 10288
    Prev
    Next
    INDEX
    Explanations

    mentions of festivals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Fest" and its variants 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
    avez
    -0.67
    MpServer
    -0.58
     clipboard
    -0.58
    loo
    -0.57
     methyl
    -0.56
     veins
    -0.55
    attled
    -0.54
    ################
    -0.54
    lly
    -0.54
    aundering
    -0.54
    POSITIVE LOGITS
    ivals
    1.62
    ivities
    1.37
    Fest
    0.99
    iversary
    0.99
     Fest
    0.98
    aign
    0.96
    ivity
    0.89
    iatus
    0.87
    fest
    0.85
    olini
    0.85
    Activations Density 0.006%

    No Known Activations