Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14048
    Prev
    Next
    INDEX
    Explanations

    details about specific events, especially related to investigations

    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
    227
    +0.12
    0.3%
    1978
    +0.10
    0.3%
    394
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    994
    +0.12
    0.03
    1978
    +0.10
    0.04
    886
    +0.10
    0.02
    Negative Logits
     erwähnten
    -0.52
     pymysql
    -0.46
     samlet
    -0.46
     moż
    -0.46
     mały
    -0.44
     manteau
    -0.44
     samoch
    -0.44
     wahre
    -0.43
    ductory
    -0.43
     pymongo
    -0.43
    POSITIVE LOGITS
     lemp
    0.86
     monaster
    0.85
     alkoh
    0.84
     keramik
    0.84
     geograf
    0.82
     Kategor
    0.82
     utop
    0.81
     marte
    0.80
     akku
    0.78
     parati
    0.78
    Activations Density 0.213%

    No Known Activations