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. 15141
    Prev
    Next
    INDEX
    Explanations

    information related to gun licenses and illegal presence

    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
    184
    +0.14
    0.4%
    1499
    +0.12
    0.3%
    964
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.14
    0.06
    1818
    +0.12
    0.05
    787
    +0.11
    0.04
    Negative Logits
    OGND
    -0.55
     '\''
    -0.53
    aarrggbb
    -0.53
     '['
    -0.52
     متعلقه
    -0.52
     awakeFromNib
    -0.52
    adaptiveStyles
    -0.52
     aidant
    -0.50
    WillAppear
    -0.50
     Winaray
    -0.48
    POSITIVE LOGITS
     fta
    1.00
     fep
    0.99
     thut
    0.95
     leaft
    0.92
     desir
    0.91
     fto
    0.88
     ftu
    0.88
     aen
    0.88
     »>
    0.86
     perfon
    0.84
    Activations Density 0.450%

    No Known Activations