© 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. 8-RES-JB
    11. 22446
    Prev
    Next
    INDEX
    Explanations

    mentions of events and activities happening on specific dates

    oai_token-act-pair · gpt-3.5-turbo

    key phrases and actions related to scheduled events or topics of public interest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kurd
    -0.74
     Boot
    -0.72
     Stats
    -0.68
     Kit
    -0.68
     Man
    -0.67
     Bard
    -0.66
     Lemon
    -0.66
     Gib
    -0.66
     Killer
    -0.65
     Pants
    -0.65
    POSITIVE LOGITS
     inver
    0.78
    cerning
    0.73
    enei
    0.71
     transc
    0.71
     ens
    0.68
     utilize
    0.68
     midst
    0.67
    uyomi
    0.67
    ENE
    0.67
     encompasses
    0.67
    Activations Density 0.288%

    No Known Activations