© 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. 12915
    Prev
    Next
    INDEX
    Explanations

    mentions of political parties and governmental systems, specifically focusing on the Republican Party and automated procurement systems in schools

    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
    1013
    +0.10
    0.3%
    513
    +0.09
    0.3%
    1820
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.10
    0.08
    24
    +0.09
    0.06
    586
    +0.08
    0.05
    Negative Logits
     impra
    -0.90
     hairc
    -0.88
     ecru
    -0.83
     autunno
    -0.80
     parch
    -0.79
     indescri
    -0.79
     swarovski
    -0.79
     scrat
    -0.79
     swee
    -0.78
     cushi
    -0.76
    POSITIVE LOGITS
     midst
    0.71
     ideolog
    0.70
     vicinity
    0.65
     context
    0.63
    存于互联网档案馆
    0.62
    <bos>
    0.60
     guise
    0.59
     ceder
    0.56
    GraphicsUnit
    0.56
     jurisdic
    0.55
    Activations Density 0.592%

    No Known Activations