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. 528
    Prev
    Next
    INDEX
    Explanations

    references to specific spans of time

    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
    1053
    +0.15
    0.6%
    1839
    +0.13
    0.5%
    1602
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1053
    +0.15
    0.06
    1602
    +0.13
    0.05
    1026
    +0.11
    0.05
    Negative Logits
     pymysql
    -0.77
     hashlib
    -0.69
     psycopg
    -0.66
     heapq
    -0.66
     pylab
    -0.64
     smtplib
    -0.62
     Hivatalos
    -0.59
     nasled
    -0.56
     naer
    -0.56
    Izvori
    -0.55
    POSITIVE LOGITS
    time
    1.15
     time
    1.11
     TIME
    1.10
    Time
    1.07
    TIME
    1.06
     Time
    1.05
    getTime
    0.84
    setTime
    0.79
    times
    0.72
     tiempo
    0.71
    Activations Density 0.152%

    No Known Activations