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. 15043
    Prev
    Next
    INDEX
    Explanations

    names of a specific individual or character

    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
    1053
    +0.16
    0.7%
    204
    +0.12
    0.5%
    1023
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1053
    +0.16
    0.02
    966
    +0.12
    0.02
    204
    +0.12
    0.02
    Negative Logits
     unspeak
    -0.72
     impelled
    -0.65
     unceasing
    -0.60
     wzgl
    -0.59
     plenti
    -0.57
     cushi
    -0.56
     indescri
    -0.55
     realizacji
    -0.55
     shewn
    -0.54
     unavoid
    -0.53
    POSITIVE LOGITS
     Jon
    1.45
    Jon
    1.38
     jon
    1.34
     JON
    1.32
     Jonathan
    1.20
    Jonathan
    1.16
    JON
    1.12
     notor
    1.04
     kön
    0.97
     Sén
    0.96
    Activations Density 0.110%

    No Known Activations