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. 6-RES-JB
    6. 14952
    Prev
    Next
    INDEX
    Explanations

    statistics related to basketball games such as points, assists, rebounds, and turnovers

    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
    50
    +0.18
    0.7%
    2036
    +0.07
    0.2%
    889
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1905
    +0.18
    0.04
    823
    +0.07
    0.03
    1355
    +0.06
    0.03
    Negative Logits
    <bos>
    -2.67
    ⓧ
    -0.90
    новништво
    -0.79
    intios
    -0.71
    RTDA
    -0.70
    public
    -0.69
    webElementXpaths
    -0.69
    autorest
    -0.68
    HasAnnotation
    -0.67
     насељу
    -0.67
    POSITIVE LOGITS
     Minang
    1.67
     impra
    1.61
     increa
    1.50
     bandung
    1.47
     lele
    1.47
     maneu
    1.46
     unspeak
    1.44
     affor
    1.44
     wien
    1.41
     stockholm
    1.40
    Activations Density 0.157%

    No Known Activations