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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7928
    Prev
    Next
    INDEX
    Explanations

    terms related to retention, especially in a professional or competitive context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    9
    +0.14
    0.5%
    369
    +0.13
    0.4%
    1233
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.14
    0.02
    9
    +0.13
    0.02
    1233
    +0.11
    0.02
    Negative Logits
     impractica
    -0.60
     Vaugh
    -0.52
     panama
    -0.51
     carter
    -0.51
     toshiba
    -0.50
     impra
    -0.49
     friable
    -0.49
     indor
    -0.49
     unlaw
    -0.48
     sessile
    -0.48
    POSITIVE LOGITS
     retain
    1.09
     retention
    0.99
     retained
    0.98
    retain
    0.98
     Retention
    0.93
     retaining
    0.92
     retains
    0.91
    RetentionPolicy
    0.81
    Retention
    0.79
    retention
    0.79
    Activations Density 0.056%

    No Known Activations