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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15266
    Prev
    Next
    INDEX
    Explanations

    terms related to reserving or setting aside resources or rights

    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
    2004
    +0.14
    0.6%
    1224
    +0.14
    0.5%
    559
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    420
    +0.14
    0.02
    559
    +0.14
    0.02
    2004
    +0.12
    0.02
    Negative Logits
     peugeot
    -0.58
     BIBSYS
    -0.56
     citroen
    -0.52
     gymnas
    -0.51
     Infatti
    -0.50
     blin
    -0.49
     Hauts
    -0.49
     impractica
    -0.49
     imposs
    -0.49
     fars
    -0.48
    POSITIVE LOGITS
     reserve
    1.46
     Reserve
    1.38
     reserves
    1.33
     Reserves
    1.29
    Reserve
    1.25
     reserved
    1.25
    reserve
    1.19
     RESERVE
    1.18
     reservation
    1.17
     RESERV
    1.14
    Activations Density 0.063%

    No Known Activations