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. 16038
    Prev
    Next
    INDEX
    Explanations

    information related to criminal activities and police investigations

    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
    198
    +0.12
    0.3%
    674
    +0.10
    0.3%
    468
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1782
    +0.12
    0.06
    415
    +0.10
    0.04
    225
    +0.10
    0.05
    Negative Logits
     swarovski
    -0.84
     vectra
    -0.84
     Février
    -0.84
     ecru
    -0.83
     fabia
    -0.81
     sappi
    -0.76
     Outils
    -0.75
     trovo
    -0.75
     mondeo
    -0.73
     peugeot
    -0.73
    POSITIVE LOGITS
     incidents
    0.69
     recent
    0.59
     recently
    0.55
    失踪
    0.54
     lately
    0.54
    Semana
    0.53
     incident
    0.52
     preliminar
    0.52
     reported
    0.51
     happening
    0.50
    Activations Density 0.640%

    No Known Activations