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. 2974
    Prev
    Next
    INDEX
    Explanations

    email addresses

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    email addresses and contact information at the end of articles.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @trainjumperx
    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
    2034
    +0.17
    0.5%
    1150
    +0.16
    0.5%
    1343
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1801
    +0.17
    0.02
    1150
    +0.16
    0.02
    1900
    +0.13
    0.02
    Negative Logits
     Ogni
    -0.85
     Queste
    -0.83
     Mentre
    -0.80
     Ciò
    -0.78
     Oltre
    -0.76
     Infatti
    -0.74
     restera
    -0.71
     Dijo
    -0.71
     Forse
    -0.70
     saurait
    -0.70
    POSITIVE LOGITS
    <bos>
    0.73
    com
    0.53
    COM
    0.51
     Chwiliwch
    0.51
    <eos>
    0.49
    mailto
    0.47
    StoreMessageInfo
    0.47
    folios
    0.46
     delimited
    0.46
    Jeografia
    0.45
    Activations Density 0.059%

    No Known Activations