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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 5613
    Prev
    Next
    INDEX
    Explanations

    references to Bangladesh and related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    544
    +0.17
    0.9%
    506
    +0.14
    0.7%
    1491
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.17
    0.04
    227
    +0.14
    0.05
    203
    +0.14
    0.03
    Negative Logits
    <bos>
    -1.38
    CloseOperation
    -0.67
    Sábado
    -0.64
    Раз
    -0.61
    Pontos
    -0.61
    PageRoute
    -0.60
    Desta
    -0.59
    Chỉ
    -0.59
    ApiOperation
    -0.58
     कॉ
    -0.58
    POSITIVE LOGITS
     depic
    1.50
     pymysql
    1.49
     Intere
    1.43
     milf
    1.34
     maneu
    1.33
     shenan
    1.32
     emphat
    1.30
     unden
    1.27
     viciss
    1.27
     hairc
    1.27
    Activations Density 0.541%

    No Known Activations