© 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. 7709
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making, attitude, and democracy

    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
    674
    +0.12
    0.3%
    198
    +0.11
    0.3%
    1446
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    705
    +0.12
    0.03
    70
    +0.11
    0.03
    835
    +0.07
    0.01
    Negative Logits
     mef
    -1.20
     Keny
    -1.18
     secon
    -1.16
     Juf
    -1.13
     excru
    -1.11
     frankfurt
    -1.11
     embra
    -1.09
     lele
    -1.08
     stockholm
    -1.08
     reluct
    -1.08
    POSITIVE LOGITS
    <bos>
    0.98
     whereas
    0.68
    findpost
    0.63
    Datuak
    0.58
    hoeddwyd
    0.58
     relatively
    0.56
     tend
    0.55
     obviously
    0.55
     easier
    0.55
     typically
    0.54
    Activations Density 0.435%

    No Known Activations