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. 1367
    Prev
    Next
    INDEX
    Explanations

    verb phrases related to human activities, strategies, and community interactions

    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
    1967
    +0.14
    0.4%
    674
    +0.08
    0.2%
    507
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1307
    +0.14
    0.02
    845
    +0.08
    0.03
    1776
    +0.07
    0.02
    Negative Logits
    InjectAttribute
    -0.85
     bezeichneter
    -0.77
    InstrumentedTest
    -0.60
    UnusedPrivate
    -0.60
    MessageOf
    -0.60
    ItemBackground
    -0.60
     كومونز
    -0.58
    fjspx
    -0.58
    SourceChecksum
    -0.58
     unknownFields
    -0.57
    POSITIVE LOGITS
    Lma
    0.85
     scrat
    0.85
    Lmfao
    0.80
    Ikr
    0.78
    FTFY
    0.78
     eyel
    0.73
    Yeet
    0.73
    UwU
    0.73
     perfet
    0.71
     milf
    0.70
    Activations Density 0.239%

    No Known Activations