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. 298
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases indicating personal opinions or experiences

    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
    2034
    +0.11
    0.3%
    1741
    +0.10
    0.3%
    1445
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.11
    0.06
    1445
    +0.10
    0.08
    62
    +0.08
    0.06
    Negative Logits
     fta
    -2.41
     increa
    -2.31
     inev
    -2.31
     effe
    -2.31
     aen
    -2.30
     mef
    -2.24
     emphat
    -2.22
     desir
    -2.19
     dises
    -2.19
     affor
    -2.18
    POSITIVE LOGITS
     myself
    1.24
     I
    1.22
     my
    1.16
     tôi
    0.90
    I
    0.90
    my
    0.89
    我
    0.87
     я
    0.84
    cshtml
    0.83
     我
    0.83
    Activations Density 0.637%

    No Known Activations