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. 15310
    Prev
    Next
    INDEX
    Explanations

    references to legal cases, political statistics, and controversial government actions

    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
    764
    +0.23
    0.7%
    1108
    +0.15
    0.5%
    1177
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.23
    0.02
    227
    +0.15
    0.03
    964
    +0.14
    0.02
    Negative Logits
     Février
    -0.66
    Noice
    -0.65
    Hahah
    -0.64
     etui
    -0.61
    FTFY
    -0.61
    Tbh
    -0.61
    Wtf
    -0.60
    Rgds
    -0.60
    LMAO
    -0.59
     Ottobre
    -0.58
    POSITIVE LOGITS
     Shakspeare
    0.57
     lii
    0.55
     cance
    0.52
     rospy
    0.51
     thut
    0.49
    AFFIRMED
    0.46
    isContained
    0.45
    enterOuterAlt
    0.45
     fath
    0.43
    mbda
    0.43
    Activations Density 0.095%

    No Known Activations