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. 2899
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the passage of time or progression

    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
    1103
    +0.14
    0.4%
    1272
    +0.10
    0.3%
    856
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1103
    +0.14
    0.05
    728
    +0.10
    0.03
    134
    +0.09
    0.03
    Negative Logits
     heapq
    -0.81
    cześ
    -0.71
     pymysql
    -0.61
     embodi
    -0.59
     psycopg
    -0.58
    ;;)
    -0.58
     smtplib
    -0.58
    xffffffff
    -0.52
     Ottobre
    -0.52
     gettyimages
    -0.50
    POSITIVE LOGITS
     July
    0.69
     December
    0.69
     June
    0.67
     February
    0.66
    by
    0.64
     November
    0.64
     August
    0.63
     January
    0.63
     April
    0.62
     September
    0.61
    Activations Density 0.148%

    No Known Activations