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. 508
    Prev
    Next
    INDEX
    Explanations

    mentions of a person named 'Ben' followed by a combination of letters

    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
    1323
    +0.16
    0.7%
    1491
    +0.14
    0.6%
    32
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1516
    +0.16
    0.03
    1323
    +0.14
    0.03
    1604
    +0.14
    0.03
    Negative Logits
     erwähnten
    -0.57
     überprüft
    -0.53
     gewährle
    -0.51
    mesine
    -0.50
     angewendet
    -0.48
     markiert
    -0.47
    miyor
    -0.47
     isoliert
    -0.47
     erkannt
    -0.46
    melidir
    -0.45
    POSITIVE LOGITS
     Ben
    1.39
     BEN
    1.36
    Ben
    1.35
     ben
    1.21
     Bén
    1.20
    BEN
    1.16
    ben
    1.02
     béné
    0.99
     Benjamin
    0.97
     Beni
    0.96
    Activations Density 0.083%

    No Known Activations