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. 15781
    Prev
    Next
    INDEX
    Explanations

    character dynamics and relationships, especially in the context of literature or storytelling

    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
    1981
    +0.13
    0.4%
    897
    +0.13
    0.4%
    410
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1981
    +0.13
    0.06
    410
    +0.13
    0.04
    990
    +0.12
    0.04
    Negative Logits
    flexDirection
    -0.47
    Descricao
    -0.46
    WriteLiteral
    -0.45
    hdysval
    -0.45
     Wahr
    -0.45
    ModelForm
    -0.44
    wych
    -0.44
    XtraEditors
    -0.44
     Karten
    -0.44
    лимпи
    -0.43
    POSITIVE LOGITS
     shenan
    0.79
     cytoplas
    0.78
     intersper
    0.77
     hentai
    0.76
     disreg
    0.75
     McLaugh
    0.71
     shayari
    0.70
     depic
    0.69
     maneu
    0.69
     Punj
    0.67
    Activations Density 0.113%

    No Known Activations