© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 858
    Prev
    Next
    INDEX
    Explanations

    phrases related to tax policies and financial matters

    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
    604
    +0.15
    0.4%
    1120
    +0.13
    0.4%
    1553
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    396
    +0.15
    0.04
    751
    +0.13
    0.05
    1519
    +0.10
    0.04
    Negative Logits
     reluct
    -1.71
     hentai
    -1.68
     milf
    -1.60
     snoopy
    -1.54
     indestru
    -1.50
     intersper
    -1.50
     madonna
    -1.47
     maneu
    -1.47
     shenan
    -1.46
     perfet
    -1.46
    POSITIVE LOGITS
     fisk
    0.82
     typelib
    0.64
    @[+][
    0.63
     Obrador
    0.62
    tgärder
    0.61
     وتسجيلات
    0.60
     proposed
    0.60
    tgär
    0.60
     dolar
    0.58
     proposals
    0.57
    Activations Density 0.486%

    No Known Activations