© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 728
    Prev
    Next
    INDEX
    Explanations

    the word "accounts"

    oai_token-act-pair · gpt-4-turbo

    accounts related to social media and communication platforms

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of accounts, particularly in social media and email contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Niet
    -0.64
    NetMessage
    -0.62
     Jinn
    -0.62
     Fulton
    -0.62
    âķIJâķIJ
    -0.61
     Valentine
    -0.60
    beam
    -0.59
     Sidd
    -0.59
    RAY
    -0.59
     ray
    -0.59
    POSITIVE LOGITS
     rece
    1.06
     accounts
    0.98
    itutional
    0.96
    pring
    0.94
    erver
    0.93
    uania
    0.92
    etting
    0.89
     balances
    0.89
     payable
    0.89
     Accounts
    0.89
    Activations Density 0.006%

    No Known Activations