© 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. 4589
    Prev
    Next
    INDEX
    Explanations

    adjectives and phrases indicating various levels of achievement or performance

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and phrases that express the quality of performance or achievement

    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
    hops
    -0.88
    aucuses
    -0.78
    ULTS
    -0.76
    ingers
    -0.72
    andals
    -0.71
    ources
    -0.71
    uits
    -0.71
     Units
    -0.70
    classes
    -0.69
    iddles
    -0.69
    POSITIVE LOGITS
     amount
    0.95
     impression
    0.90
     dose
    0.89
     foothold
    0.87
     comeback
    0.87
     berth
    0.85
     glance
    0.83
     chunk
    0.81
     burden
    0.79
     bead
    0.78
    Activations Density 0.248%

    No Known Activations