Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 19463
    Prev
    Next
    INDEX
    Explanations

    information related to news reports and public communication

    oai_token-act-pair · gpt-3.5-turbo

    calls to action related to reporting or providing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avored
    -0.89
     favors
    -0.88
    defense
    -0.87
     favoring
    -0.86
    imize
    -0.85
    colored
    -0.84
     unfavorable
    -0.83
     utilized
    -0.82
     favor
    -0.82
     favorable
    -0.81
    POSITIVE LOGITS
     £
    1.67
     NHS
    1.48
     UKIP
    1.45
     Yorkshire
    1.44
     Ukip
    1.43
    Scotland
    1.41
    £
    1.39
     Scotland
    1.36
     Belfast
    1.36
     Labour
    1.35
    Activations Density 2.025%

    No Known Activations