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. 1761
    Prev
    Next
    INDEX
    Explanations

    information about historical events and territorial organizations, specifically related to Cossack societies and states

    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
    184
    +0.36
    1.2%
    1842
    +0.20
    0.7%
    137
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.36
    0.04
    137
    +0.20
    0.09
    845
    +0.16
    0.03
    Negative Logits
     ecclesias
    -0.80
     ristor
    -0.75
     gti
    -0.72
     soggior
    -0.72
     ladri
    -0.71
     affari
    -0.71
     vacanze
    -0.70
     peculi
    -0.70
    tempts
    -0.70
     igno
    -0.69
    POSITIVE LOGITS
    Nieuwe
    0.50
    optarg
    0.45
    Från
    0.44
    Madre
    0.44
    Inne
    0.42
    ilustra
    0.41
    مقاله
    0.41
    glBindBuffer
    0.40
    livro
    0.40
    können
    0.40
    Activations Density 0.627%

    No Known Activations