© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23741
    Prev
    Next
    INDEX
    Explanations

    superlatives or words related to extremity

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "most" in various contexts

    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
    heid
    -0.74
    rompt
    -0.74
    pload
    -0.72
    æ©
    -0.71
    oak
    -0.67
     Films
    -0.64
     Recording
    -0.63
    ategories
    -0.63
     Oaks
    -0.62
    instead
    -0.61
    POSITIVE LOGITS
     important
    0.98
    likely
    0.91
     obvious
    0.90
     plausible
    0.89
     likely
    0.87
     efficient
    0.87
     profitable
    0.85
     importantly
    0.84
     noticeable
    0.84
     prominent
    0.84
    Activations Density 0.058%

    No Known Activations