© 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. 1499
    Prev
    Next
    INDEX
    Explanations

    comparisons between two entities, especially highlighting the second mentioned entity

    oai_token-act-pair · gpt-3.5-turbo

    the term "latter" in various contexts indicating comparisons or distinctions

    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
     Clover
    -0.70
    9999
    -0.70
    cars
    -0.69
     Cars
    -0.68
    arij
    -0.68
    Cola
    -0.68
    Magn
    -0.67
    grid
    -0.67
    oku
    -0.64
    hers
    -0.63
    POSITIVE LOGITS
    mentioned
    0.91
     stages
    0.85
    ingly
    0.73
    nder
    0.73
    worldly
    0.69
    most
    0.69
     part
    0.68
     dilig
    0.68
     type
    0.66
     sort
    0.66
    Activations Density 0.034%

    No Known Activations