© 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. 8-RES-JB
    11. 22576
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a situation or event occurring within a larger context

    oai_token-act-pair · gpt-3.5-turbo

    the word "amid" and its variants indicating contexts of chaos or crisis

    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
    ammed
    -0.70
    IPP
    -0.69
    quote
    -0.68
    LP
    -0.68
    imei
    -0.67
    wright
    -0.66
    ared
    -0.66
    authors
    -0.66
     lucky
    -0.65
    miah
    -0.65
    POSITIVE LOGITS
     fears
    0.99
     rumours
    0.90
     controversy
    0.88
     tensions
    0.85
     uncertainty
    0.85
     rumors
    0.82
     turmoil
    0.82
     allegations
    0.81
    ĸļ
    0.81
     suspicions
    0.81
    Activations Density 0.038%

    No Known Activations