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. 324
    Prev
    Next
    INDEX
    Explanations

    names of individuals related to legal or political matters

    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
    1150
    +0.24
    0.7%
    1842
    +0.20
    0.6%
    227
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.24
    0.08
    227
    +0.20
    0.08
    1364
    +0.13
    0.06
    Negative Logits
     affez
    -0.98
     coö
    -0.90
     unden
    -0.83
     giusti
    -0.82
     HEW
    -0.75
     aen
    -0.74
     socie
    -0.72
     usati
    -0.72
     Expt
    -0.72
     dimentic
    -0.72
    POSITIVE LOGITS
     whose
    0.65
    .
    0.64
     who
    0.63
     whom
    0.60
    whose
    0.54
    who
    0.54
     during
    0.51
    。
    0.51
     blancas
    0.50
    ATEGY
    0.49
    Activations Density 0.366%

    No Known Activations