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. 14968
    Prev
    Next
    INDEX
    Explanations

    information related to research projects and reports, especially focusing on findings and researchers

    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
    169
    +0.16
    0.6%
    950
    +0.15
    0.6%
    663
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    169
    +0.16
    0.05
    663
    +0.15
    0.05
    950
    +0.15
    0.06
    Negative Logits
     velours
    -0.67
     Faculté
    -0.54
     pittores
    -0.54
     Gallimard
    -0.54
    箕
    -0.53
     Compt
    -0.53
     dynamis
    -0.52
     Foire
    -0.51
     impon
    -0.51
     fré
    -0.50
    POSITIVE LOGITS
     research
    1.29
    research
    1.17
     Research
    1.16
    Research
    1.14
     RESEARCH
    1.09
    RESEARCH
    1.04
     researches
    1.02
     researchers
    0.96
     researched
    0.91
     researcher
    0.91
    Activations Density 0.099%

    No Known Activations