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. 7768
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to mental health and behavioral changes

    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
    +0.38
    1.3%
    604
    +0.09
    0.3%
    906
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    595
    +0.38
    0.05
    1553
    +0.09
    0.07
    736
    +0.09
    0.07
    Negative Logits
    <bos>
    -1.76
    ClientSize
    -0.56
    Referències
    -0.56
     evangé
    -0.55
     respecte
    -0.52
     persa
    -0.50
     pous
    -0.50
     profili
    -0.49
    //
    -0.49
    public
    -0.48
    POSITIVE LOGITS
     pymysql
    1.39
     smtplib
    1.22
     heapq
    1.13
     pylab
    1.10
     hashlib
    1.08
     psycopg
    1.07
     dott
    1.02
     Jambi
    1.01
     pymongo
    0.96
     scatt
    0.93
    Activations Density 1.141%

    No Known Activations