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. 9-RES-JB
    6. 22576
    Prev
    Next
    INDEX
    Explanations

    words related to countries, government, and policies

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms indicating belonging or association with a country

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    epad
    -0.67
    potion
    -0.62
    ording
    -0.61
    Reference
    -0.58
    iator
    -0.57
    osponsors
    -0.56
    yz
    -0.56
     targ
    -0.56
     sacrific
    -0.55
    animous
    -0.55
    POSITIVE LOGITS
     largest
    1.03
    largest
    0.91
     poorest
    0.89
     tallest
    0.88
     finest
    0.86
     premier
    0.85
     borders
    0.85
     foremost
    0.85
     longest
    0.81
    urgical
    0.81
    Activations Density 0.122%

    No Known Activations