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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 8049
    Prev
    Next
    INDEX
    Explanations

    phrases related to passwords and access credentials

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    285
    +0.12
    0.5%
    35
    +0.10
    0.5%
    473
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    285
    +0.12
    0.01
    522
    +0.10
    0.01
    473
    +0.09
    0.01
    Negative Logits
    rums
    -0.78
     Galile
    -0.69
     guiActiveUnfocused
    -0.68
    Ĥ¬
    -0.68
    nih
    -0.67
    nian
    -0.66
    shows
    -0.64
    builders
    -0.64
    axies
    -0.64
    ICLE
    -0.63
    POSITIVE LOGITS
     password
    1.07
     passwords
    1.02
     Password
    0.91
     hashes
    0.90
     login
    0.88
    password
    0.88
     authentication
    0.88
     captcha
    0.85
     hash
    0.84
     hashing
    0.82
    Activations Density 0.016%

    No Known Activations