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. 13531
    Prev
    Next
    INDEX
    Explanations

    information related to historical events and social issues

    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
    453
    +0.16
    0.5%
    776
    +0.12
    0.4%
    1978
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    321
    +0.16
    0.08
    776
    +0.12
    0.06
    573
    +0.11
    0.05
    Negative Logits
    <bos>
    -1.60
     unspeak
    -1.34
     gratify
    -1.13
     philosophic
    -1.13
     ardour
    -1.10
     endeavouring
    -1.09
     vainly
    -1.08
     luxuriant
    -1.08
     tolerably
    -1.07
     sophistic
    -1.07
    POSITIVE LOGITS
     alkoh
    1.92
     silikon
    1.87
     utop
    1.81
     mikrofon
    1.75
     spion
    1.74
     makro
    1.73
     kosme
    1.71
     keramik
    1.65
     kask
    1.64
     elek
    1.64
    Activations Density 0.161%

    No Known Activations