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. 579
    Prev
    Next
    INDEX
    Explanations

    mentions of gang-related activities

    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
    896
    +0.13
    0.5%
    537
    +0.12
    0.4%
    156
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    896
    +0.13
    0.01
    130
    +0.12
    0.02
    537
    +0.10
    0.02
    Negative Logits
    onomian
    -0.54
     كومونز
    -0.54
    SystemColors
    -0.52
    STRUCTIONS
    -0.47
     kona
    -0.46
    Flere
    -0.45
    AddWithValue
    -0.45
    AndroidJUnit
    -0.44
     vern
    -0.44
    atience
    -0.44
    POSITIVE LOGITS
     gang
    1.35
     Gang
    1.30
    Gang
    1.29
    gang
    1.10
     gangs
    1.05
    gangs
    0.94
     Ibidem
    0.63
    Ikr
    0.61
     ganger
    0.59
     quæ
    0.57
    Activations Density 0.062%

    No Known Activations