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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 7-RES-JB
    6. 6568
    Prev
    Next
    INDEX
    Explanations

    the word "city" followed by other words

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific company or organization

    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
    dress
    -0.64
     veins
    -0.62
     disbelief
    -0.61
     bait
    -0.60
    pires
    -0.59
    mith
    -0.58
     tissue
    -0.57
    lycer
    -0.57
     reception
    -0.57
     conqu
    -0.57
    POSITIVE LOGITS
    ality
    1.20
    eca
    1.07
    agraph
    1.03
    osphere
    1.02
    ally
    0.99
    rix
    0.99
    erva
    0.95
    ems
    0.95
    izen
    0.91
    tering
    0.90
    Activations Density 0.055%

    No Known Activations