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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 6707
    Prev
    Next
    INDEX
    Explanations

    references to the Tamil Nadu political landscape and its parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.13
    0.5%
    860
    +0.10
    0.4%
    240
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.13
    0.04
    860
    +0.10
    0.02
    1343
    +0.10
    0.03
    Negative Logits
    <bos>
    -1.96
    ⓧ
    -0.76
    </thead>
    -0.68
    ">—
    -0.60
    терак
    -0.59
     avesse
    -0.59
    ;%%
    -0.59
    DOCTYPE
    -0.59
    ersonal
    -0.59
     złotych
    -0.59
    POSITIVE LOGITS
     affor
    1.60
     Bartholo
    1.57
     unspeak
    1.54
     Mlle
    1.53
     Thos
    1.53
     unden
    1.52
     »>
    1.49
     thut
    1.49
     indescri
    1.48
     Gorb
    1.47
    Activations Density 0.125%

    No Known Activations