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. 15901
    Prev
    Next
    INDEX
    Explanations

    descriptions of things that someone wants to do or show

    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
    1323
    +0.12
    0.4%
    1271
    +0.11
    0.4%
    1325
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1053
    +0.12
    0.03
    1325
    +0.11
    0.03
    1235
    +0.10
    0.04
    Negative Logits
     perfon
    -0.86
     sovere
    -0.85
     fta
    -0.82
     nece
    -0.82
     palab
    -0.81
     fte
    -0.78
     electrica
    -0.78
     inol
    -0.78
     castro
    -0.77
     embra
    -0.77
    POSITIVE LOGITS
     wanted
    0.93
    wanted
    0.81
     Wanted
    0.78
    Wanted
    0.74
     WANTED
    0.72
     hadn
    0.59
     knew
    0.56
     needed
    0.55
    WANTED
    0.54
     NEEDED
    0.53
    Activations Density 0.153%

    No Known Activations