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. 10070
    Prev
    Next
    INDEX
    Explanations

    phrases related to power dynamics and legal proceedings

    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
    50
    +0.21
    0.8%
    1150
    +0.14
    0.5%
    1108
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.21
    0.01
    163
    +0.14
    0.01
    382
    +0.13
    0.04
    Negative Logits
    <bos>
    -1.43
     CiNii
    -0.71
     exé
    -0.71
     aspetta
    -0.68
     amitié
    -0.67
     pitié
    -0.67
    ⓧ
    -0.66
    <?
    -0.66
     pourrais
    -0.65
     Áng
    -0.65
    POSITIVE LOGITS
    RectF
    0.53
    falgar
    0.50
    HttpDelete
    0.49
    })}\
    0.45
    TextWatcher
    0.45
     Salida
    0.45
    IBOutlet
    0.44
    usermodel
    0.42
    Reentrant
    0.42
    ********/
    0.41
    Activations Density 0.467%

    No Known Activations