© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 13956
    Prev
    Next
    INDEX
    Explanations

    phrases indicating argumentation or presenting a claim in a legal or formal context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "that" and phrases indicating claims or arguments

    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
    aukee
    -0.76
    ggles
    -0.69
    alt
    -0.68
    Laughs
    -0.68
    estern
    -0.68
    ãĤ´ãĥ³
    -0.67
    âĹ¼
    -0.67
     redes
    -0.67
    guard
    -0.66
    ET
    -0.66
    POSITIVE LOGITS
     they
    0.83
     excessive
    0.73
     inadequate
    0.72
    cher
    0.70
     unfairly
    0.69
     although
    0.68
     it
    0.67
     improper
    0.67
     insufficient
    0.67
     delaying
    0.67
    Activations Density 0.207%

    No Known Activations