© 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. 13848
    Prev
    Next
    INDEX
    Explanations

    phrases describing personal or professional actions taken against individuals

    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
    1678
    +0.12
    0.4%
    32
    +0.12
    0.4%
    478
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    32
    +0.12
    0.10
    68
    +0.12
    0.08
    1678
    +0.11
    0.09
    Negative Logits
     bordeaux
    -0.97
     napoli
    -0.92
     milano
    -0.90
     lyon
    -0.89
     fuj
    -0.88
     écl
    -0.87
     ibiza
    -0.86
     oreo
    -0.86
     thermomix
    -0.86
     levis
    -0.85
    POSITIVE LOGITS
     been
    0.81
     become
    0.68
    been
    0.68
     had
    0.62
     BEEN
    0.61
     come
    0.61
     gone
    0.61
     reportedly
    0.60
     has
    0.56
     already
    0.56
    Activations Density 0.453%

    No Known Activations