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. 13513
    Prev
    Next
    INDEX
    Explanations

    names of football players or individuals

    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
    204
    +0.15
    0.7%
    200
    +0.15
    0.6%
    1053
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    200
    +0.15
    0.02
    204
    +0.15
    0.02
    1053
    +0.14
    0.02
    Negative Logits
    Atsauces
    -0.64
    zurück
    -0.59
    település
    -0.57
    wieś
    -0.57
    Parmi
    -0.56
    Törté
    -0.53
    Formazione
    -0.53
    municipi
    -0.52
    Další
    -0.51
    více
    -0.51
    POSITIVE LOGITS
     Jones
    1.62
    Jones
    1.48
    jones
    1.36
     JONES
    1.34
     jones
    1.28
     Machine
    0.66
    Machine
    0.64
    machine
    0.64
     machine
    0.64
    machines
    0.61
    Activations Density 0.089%

    No Known Activations