© 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. 16348
    Prev
    Next
    INDEX
    Explanations

    words related to places or establishments, specifically those ending in -arium

    oai_token-act-pair · gpt-3.5-turbo

    words related to aquariums and related settings

    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
     confident
    -0.69
     confidence
    -0.66
     hands
    -0.65
     Turks
    -0.61
     Hand
    -0.61
     folds
    -0.60
     unh
    -0.60
     hand
    -0.60
     knock
    -0.60
     regret
    -0.59
    POSITIVE LOGITS
    arium
    4.66
    arius
    2.69
    aria
    1.87
    arian
    1.59
    aries
    1.47
    arie
    1.47
    arial
    1.36
    arist
    1.35
    arians
    1.35
    arious
    1.31
    Activations Density 0.006%

    No Known Activations