© 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. 9-RES-JB
    11. 3629
    Prev
    Next
    INDEX
    Explanations

    mentions of temporary or quickly established entities, such as pop-up events or restaurants

    oai_token-act-pair · gpt-3.5-turbo

    references to "pop-up" concepts or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¿½
    -0.75
     Cohn
    -0.72
     extent
    -0.67
     Howe
    -0.66
     workings
    -0.65
     Vance
    -0.63
     Corm
    -0.61
     Daly
    -0.60
     geometry
    -0.60
     Commons
    -0.59
    POSITIVE LOGITS
    insula
    0.94
    culture
    0.91
    art
    0.88
    eared
    0.85
    vertising
    0.84
    interstitial
    0.80
    ream
    0.79
    rush
    0.79
    shoot
    0.79
    up
    0.78
    Activations Density 0.062%

    No Known Activations