© 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. 3414
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal issues and public opinions

    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
    1919
    +0.12
    0.3%
    2006
    +0.11
    0.3%
    1265
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2006
    +0.12
    0.06
    1919
    +0.11
    0.06
    908
    +0.09
    0.04
    Negative Logits
     cioc
    -0.88
     isolato
    -0.88
     buc
    -0.85
     kasa
    -0.83
     libere
    -0.81
     répon
    -0.81
     riman
    -0.79
     torba
    -0.78
     ordina
    -0.78
     elek
    -0.78
    POSITIVE LOGITS
    ఔ
    0.59
     believe
    0.59
    SneakyThrows
    0.57
     assume
    0.54
     would
    0.53
     have
    0.53
     mergeFrom
    0.52
     underestimate
    0.52
     prefer
    0.51
    OGND
    0.51
    Activations Density 0.291%

    No Known Activations