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. 8427
    Prev
    Next
    INDEX
    Explanations

    information about achievements and contributions of individuals

    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
    1108
    +0.12
    0.4%
    581
    +0.10
    0.3%
    1892
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1108
    +0.12
    0.06
    1450
    +0.10
    0.02
    109
    +0.08
    0.04
    Negative Logits
     vns
    -1.23
     ftu
    -1.22
     ftre
    -1.20
     hcm
    -1.19
     fays
    -1.18
     fta
    -1.18
     depic
    -1.18
     perfon
    -1.16
     eduardo
    -1.16
     sovere
    -1.16
    POSITIVE LOGITS
     Wicidata
    0.54
    aarrggbb
    0.54
     And
    0.53
    retario
    0.52
    And
    0.52
     importantly
    0.49
    Hozzáférés
    0.49
    adaptiveStyles
    0.48
     yes
    0.47
    บัติ
    0.47
    Activations Density 0.371%

    No Known Activations