Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8123
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal charges or criminal 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
    74
    +0.10
    0.3%
    453
    +0.09
    0.3%
    783
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.10
    0.06
    1415
    +0.09
    0.03
    1417
    +0.09
    0.04
    Negative Logits
     bourgeo
    -0.83
     Souha
    -0.77
     Bartholo
    -0.76
     cannes
    -0.76
     Juf
    -0.74
     soigne
    -0.73
     Hermans
    -0.73
     emphat
    -0.72
     Rine
    -0.71
    oine
    -0.71
    POSITIVE LOGITS
    also
    0.99
     also
    0.97
     ALSO
    0.88
     também
    0.87
    también
    0.86
     también
    0.82
     també
    0.81
    Also
    0.81
     også
    0.75
     також
    0.75
    Activations Density 0.539%

    No Known Activations