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. 2-RES-JB
    6. 16678
    Prev
    Next
    INDEX
    Explanations

    mentions of historical revolutions or related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to various revolutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OTH
    -0.77
    cedented
    -0.76
    %%%%
    -0.75
     spaced
    -0.72
    odynamic
    -0.68
    ĻĤ
    -0.67
    thy
    -0.67
    à
    -0.66
    umn
    -0.66
    gettable
    -0.65
    POSITIVE LOGITS
    aries
    1.21
     Revolution
    1.18
    naire
    1.18
    aire
    0.88
     Launcher
    0.82
     Router
    0.81
    naires
    0.80
    eers
    0.80
    urrection
    0.79
    acion
    0.78
    Activations Density 0.012%

    No Known Activations