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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 3-RES-JB
    6. 19671
    Prev
    Next
    INDEX
    Explanations

    references to political action committees (PACs) and their affiliations

    oai_token-act-pair · gpt-3.5-turbo

    references to political action committees (PACs)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çīĪ
    -0.77
    lihood
    -0.70
    Charges
    -0.67
     Hes
    -0.66
     Portug
    -0.64
    glass
    -0.61
    pots
    -0.60
    íķ
    -0.60
     Brazilian
    -0.59
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.58
    POSITIVE LOGITS
    IFIC
    1.23
    eers
    1.07
    PAC
    1.00
    regate
    0.89
     treasurer
    0.86
    ocobo
    0.86
    BLIC
    0.83
     committees
    0.81
    regor
    0.80
    rons
    0.78
    Activations Density 0.006%

    No Known Activations