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. 15648
    Prev
    Next
    INDEX
    Explanations

    URLs with a specific address and placeholder text related to tasks and notes

    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
    453
    +0.26
    0.8%
    2019
    +0.22
    0.7%
    605
    +0.19
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.26
    0.05
    981
    +0.22
    0.04
    605
    +0.19
    0.01
    Negative Logits
     fta
    -1.52
     wien
    -1.51
     snoopy
    -1.46
     fei
    -1.46
     Juf
    -1.43
     secon
    -1.42
     intermitt
    -1.41
     fup
    -1.40
     ftu
    -1.40
     vns
    -1.40
    POSITIVE LOGITS
    frac
    0.71
    super
    0.68
    public
    0.67
    enumerate
    0.65
    begin
    0.65
    get
    0.64
    multicolumn
    0.64
    custom
    0.64
    boldsymbol
    0.64
     برابوك
    0.63
    Activations Density 0.116%

    No Known Activations