© 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. 3334
    Prev
    Next
    INDEX
    Explanations

    instances where actions, characteristics, or emotions of individuals are depicted in a negative light

    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
    869
    +0.11
    0.3%
    966
    +0.09
    0.3%
    1482
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    869
    +0.11
    0.05
    966
    +0.09
    0.04
    1482
    +0.08
    0.03
    Negative Logits
     pamph
    -0.69
     shenan
    -0.64
     calum
    -0.64
     berea
    -0.62
     impractica
    -0.62
     unspeak
    -0.61
     Rine
    -0.61
     Debates
    -0.61
     Standardi
    -0.60
     evoc
    -0.59
    POSITIVE LOGITS
     SHOW
    0.71
     signes
    0.68
     tyn
    0.67
     fras
    0.67
     tenda
    0.66
    showed
    0.65
    SHOW
    0.65
     SHOWING
    0.65
     dollari
    0.64
    show
    0.64
    Activations Density 0.170%

    No Known Activations