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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 3011
    Prev
    Next
    INDEX
    Explanations

    words related to expressing opinions or drawing conclusions

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating conclusions and ongoing discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transformative
    -0.64
     generational
    -0.61
     pend
    -0.59
     diaper
    -0.58
    osate
    -0.57
     Lot
    -0.55
     Workers
    -0.55
    ffield
    -0.54
     fragmentation
    -0.54
     underestimated
    -0.54
    POSITIVE LOGITS
     rhet
    0.72
    Laughs
    0.70
     Vaugh
    0.70
    ãĥ´
    0.70
    Tokens
    0.67
     quoting
    0.66
    _.
    0.66
     sarcast
    0.65
    mson
    0.63
    said
    0.62
    Activations Density 0.160%

    No Known Activations