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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 2504
    Prev
    Next
    INDEX
    Explanations

    personal information related to self-introduction, personal preferences, and lifestyle details

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.21
    0.9%
    736
    +0.14
    0.6%
    1978
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.21
    0.15
    381
    +0.14
    0.01
    1408
    +0.09
    0.08
    Negative Logits
    <bos>
    -2.77
    SequentialGroup
    -0.84
    ByVersion
    -0.84
    ImageContext
    -0.83
    DoubleQuotes
    -0.82
    Configurer
    -0.81
    Chham
    -0.80
     Distrikt
    -0.80
     Walkover
    -0.78
    Referències
    -0.78
    POSITIVE LOGITS
     reluct
    2.82
     affor
    2.78
     impra
    2.76
     disagre
    2.69
     shenan
    2.62
     accla
    2.61
     indestru
    2.60
     unspeak
    2.56
     maneu
    2.56
     unwarran
    2.54
    Activations Density 3.444%

    No Known Activations