© 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. 6-RES-JB
    11. 20388
    Prev
    Next
    INDEX
    Explanations

    superlatives and comparisons

    oai_token-act-pair · gpt-3.5-turbo

    superlative adjectives and comparative phrases, particularly those describing methods or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    azard
    -0.78
    ipel
    -0.73
    avis
    -0.73
    utics
    -0.68
    apons
    -0.66
    ammed
    -0.66
    poke
    -0.66
    apesh
    -0.65
    jong
    -0.64
    iky
    -0.63
    POSITIVE LOGITS
     thing
    1.06
     question
    1.03
     downside
    1.01
     reason
    1.01
     takeaway
    0.96
     drawback
    0.96
     exception
    0.91
     caveat
    0.89
     concern
    0.82
     straw
    0.82
    Activations Density 0.224%

    No Known Activations