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 · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 12-RES-JB
    6. 158
    Prev
    Next
    INDEX
    Explanations

    first-person experiences and actions related to personal growth and reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.12.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    12
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.38
    1.3%
    453
    +0.11
    0.4%
    381
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.38
    0.14
    862
    +0.11
    0.09
    1415
    +0.11
    0.10
    Negative Logits
    <bos>
    -1.21
     intersper
    -0.89
     oleo
    -0.85
     répon
    -0.85
     soigne
    -0.82
     cushi
    -0.81
     exé
    -0.79
     overcrow
    -0.78
     tupperware
    -0.77
     quitted
    -0.74
    POSITIVE LOGITS
     Banten
    0.70
     Muhamma
    0.69
     smtplib
    0.69
    Estou
    0.69
    alnız
    0.69
    dónde
    0.68
     Lampung
    0.67
    Quiénes
    0.66
    Ótimo
    0.66
    GEBURTSDATUM
    0.65
    Activations Density 1.121%

    No Known Activations