Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8057
    Prev
    Next
    INDEX
    Explanations

    numerals indicating quantities and details about costs and construction

    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
    678
    +0.19
    0.6%
    1177
    +0.13
    0.4%
    227
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.19
    0.10
    16
    +0.13
    0.08
    776
    +0.13
    0.06
    Negative Logits
    phazard
    -0.79
     leksikon
    -0.69
     linke
    -0.66
     odkazy
    -0.66
     doInBackground
    -0.65
     onAnimation
    -0.62
     esboço
    -0.62
     insuffisamment
    -0.61
    enderror
    -0.61
     trist
    -0.60
    POSITIVE LOGITS
     sophistic
    1.32
     philanth
    1.21
     shenan
    1.18
     impra
    1.18
     intrigu
    1.17
     unspeak
    1.13
     pamph
    1.12
     impractica
    1.05
     reluct
    1.05
     cushi
    1.00
    Activations Density 0.718%

    No Known Activations