© 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. 0-RES-JB
    11. 19882
    Prev
    Next
    INDEX
    Explanations

    phrases related to festivities or commemorations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "celebrating" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lin
    -0.74
    ient
    -0.63
    ither
    -0.62
    Rat
    -0.61
     unreliable
    -0.61
    ¶
    -0.61
     Input
    -0.60
    onz
    -0.59
    rg
    -0.59
     Seller
    -0.59
    POSITIVE LOGITS
     celebrating
    3.49
     celebrate
    2.44
     commemor
    2.27
     celebrates
    2.27
     celebrations
    2.26
     celebration
    2.22
     Celebr
    2.16
     celebr
    2.03
     celebrated
    1.94
     honoring
    1.86
    Activations Density 0.020%

    No Known Activations