© 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. 8-RES-JB
    6. 2309
    Prev
    Next
    INDEX
    Explanations

    sentences ending with a period

    oai_token-act-pair · gpt-3.5-turbo

    statements or claims about political events or issues

    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
     advoc
    -0.77
     activ
    -0.70
     docks
    -0.68
     targ
    -0.68
     sal
    -0.67
     oak
    -0.67
     tyr
    -0.65
    thal
    -0.65
     unstoppable
    -0.64
     therape
    -0.64
    POSITIVE LOGITS
     Instead
    1.87
     Nor
    1.62
     Nonetheless
    1.52
     Neither
    1.49
     Nevertheless
    1.49
    Instead
    1.46
     Rather
    1.42
    Nevertheless
    1.29
     Consequently
    1.28
    Nonetheless
    1.27
    Activations Density 0.595%

    No Known Activations