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. 0-RES-JB
    6. 20644
    Prev
    Next
    INDEX
    Explanations

    mentions of the organization Antifa

    oai_token-act-pair · gpt-3.5-turbo

    references to the Antifa movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     magnetic
    -0.70
     pen
    -0.67
     cycl
    -0.64
     cent
    -0.63
     landing
    -0.62
     dro
    -0.62
     cycle
    -0.62
     process
    -0.62
     depths
    -0.61
     Nickel
    -0.61
    POSITIVE LOGITS
    ifa
    4.68
    IFA
    2.00
    afa
    1.27
    ouf
    1.23
     Fifa
    1.12
    abi
    1.05
    amiya
    1.04
    Fa
    1.02
    isma
    0.99
    if
    0.99
    Activations Density 0.009%

    No Known Activations