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. 1750
    Prev
    Next
    INDEX
    Explanations

    information related to historical events and figures, particularly surrounding births, deaths, and notable actions

    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
    1842
    +0.10
    0.3%
    581
    +0.10
    0.3%
    1013
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1117
    +0.10
    0.03
    509
    +0.10
    0.05
    908
    +0.09
    0.02
    Negative Logits
    lectoral
    -0.51
    Derbyniad
    -0.47
    Organisateur
    -0.47
    jsdelivr
    -0.47
    clectic
    -0.47
     linkovi
    -0.44
    WithIOException
    -0.44
     PicClick
    -0.42
    ByVersion
    -0.42
    Coordonnées
    -0.42
    POSITIVE LOGITS
     disagre
    0.81
     suspic
    0.81
     shenan
    0.79
     reluct
    0.79
     infant
    0.78
     newborn
    0.77
     excru
    0.76
     babies
    0.75
     inev
    0.74
     newborns
    0.73
    Activations Density 0.403%

    No Known Activations