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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13758
    Prev
    Next
    INDEX
    Explanations

    references to military activities and technology

    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
    297
    +0.12
    0.4%
    368
    +0.09
    0.3%
    1042
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    297
    +0.12
    0.05
    368
    +0.09
    0.04
    284
    +0.09
    0.05
    Negative Logits
     emphat
    -1.05
     purcha
    -1.04
     increa
    -1.01
     desir
    -1.01
     ?...
    -1.01
     attemp
    -1.00
     inev
    -1.00
     laun
    -0.98
     reluct
    -0.98
     apprehen
    -0.97
    POSITIVE LOGITS
    <bos>
    0.79
     Full
    0.77
    Full
    0.76
    FULL
    0.75
    full
    0.73
     full
    0.72
    WriteTagHelper
    0.65
     FULL
    0.64
     Fully
    0.63
     fully
    0.62
    Activations Density 0.412%

    No Known Activations