© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 4508
    Prev
    Next
    INDEX
    Explanations

    references to specific locations, possibly related to crimes or incidents happening in those places

    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
    577
    +0.12
    0.3%
    1510
    +0.11
    0.3%
    1967
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    507
    +0.12
    0.04
    577
    +0.11
    0.04
    1370
    +0.10
    0.04
    Negative Logits
     heapq
    -0.69
    Eksteraj
    -0.67
     pymysql
    -0.61
     hashlib
    -0.59
    Iné
    -0.58
    bardziej
    -0.58
    Alguna
    -0.58
    Ekster
    -0.56
    Să
    -0.56
    Przyp
    -0.55
    POSITIVE LOGITS
     leonardo
    0.94
     ricardo
    0.93
     jorge
    0.92
     gabriel
    0.91
     gabri
    0.90
     sergio
    0.89
     teresa
    0.89
     jared
    0.86
     yoda
    0.85
     milf
    0.85
    Activations Density 0.084%

    No Known Activations