Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15734
    Prev
    Next
    INDEX
    Explanations

    historical and political terms related to freedom, democracy, and activism

    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
    752
    +0.14
    0.4%
    1983
    +0.09
    0.3%
    1381
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1334
    +0.14
    0.03
    752
    +0.09
    0.03
    1983
    +0.09
    0.03
    Negative Logits
     gedurende
    -0.54
     withal
    -0.50
    OrEmpty
    -0.49
    PerSecond
    -0.48
    mnop
    -0.45
    šech
    -0.44
    Hashes
    -0.43
     gebou
    -0.43
    setzer
    -0.42
    utched
    -0.42
    POSITIVE LOGITS
     kram
    0.70
     logis
    0.68
     sembrano
    0.66
     tomat
    0.66
     rendono
    0.66
     Nö
    0.65
     minimalis
    0.65
     kado
    0.63
    Bibliograf
    0.63
     ridu
    0.63
    Activations Density 0.303%

    No Known Activations