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. 15714
    Prev
    Next
    INDEX
    Explanations

    information or instructions presented sequentially, possibly in a tutorial format

    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
    1828
    +0.16
    0.6%
    31
    +0.13
    0.5%
    674
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1828
    +0.16
    0.05
    156
    +0.13
    0.04
    31
    +0.12
    0.04
    Negative Logits
     santiago
    -0.88
     yong
    -0.77
     nuoc
    -0.76
     Jusqu
    -0.73
     thuy
    -0.71
     Leurs
    -0.70
     lele
    -0.69
     yaa
    -0.68
     mahd
    -0.68
     Celui
    -0.67
    POSITIVE LOGITS
     on
    0.81
     ON
    0.78
     On
    0.76
    On
    0.64
    on
    0.60
     onto
    0.58
     delà
    0.53
    ON
    0.53
     Onco
    0.53
     sentier
    0.52
    Activations Density 0.146%

    No Known Activations