© 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. 7-RES-JB
    11. 17137
    Prev
    Next
    INDEX
    Explanations

    references to user accounts, email addresses, and account-related actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "account"

    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
     Sight
    -0.75
    NetMessage
    -0.71
    GGGGGGGG
    -0.70
    ————
    -0.65
    GGGG
    -0.64
     intrins
    -0.62
    beam
    -0.62
    seq
    -0.61
     Aki
    -0.61
     lact
    -0.61
    POSITIVE LOGITS
    ancy
    1.19
     balances
    1.12
     rece
    1.06
     holders
    1.05
     holder
    1.04
    abilities
    1.00
    ants
    0.97
     payable
    0.94
    lain
    0.88
    ngth
    0.81
    Activations Density 0.035%

    No Known Activations