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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 12-RES-JB
    6. 189
    Prev
    Next
    INDEX
    Explanations

    financial indicators and stock market performance metrics

    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.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.12.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    12
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.15
    0.5%
    604
    +0.08
    0.3%
    453
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1978
    +0.15
    0.03
    1445
    +0.08
    0.03
    859
    +0.07
    0.03
    Negative Logits
    <bos>
    -2.61
    ⓧ
    -1.33
     intersper
    -1.32
     fuf
    -1.15
     embra
    -1.10
    
    
    -1.09
     encomp
    -1.04
    <?
    -1.04
    /**
    -1.03
     congr
    -1.02
    POSITIVE LOGITS
    ]=$
    0.61
     patata
    0.58
     jawa
    0.58
    9
    0.57
     gentes
    0.56
     cabina
    0.55
     doña
    0.55
     pisang
    0.55
     Där
    0.55
    ))-
    0.54
    Activations Density 0.078%

    No Known Activations