© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10682
    Prev
    Next
    INDEX
    Explanations

    references to political reality, plans, and consequences

    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
    1804
    +0.11
    0.3%
    1150
    +0.11
    0.3%
    599
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    919
    +0.11
    0.03
    280
    +0.11
    0.06
    1705
    +0.10
    0.07
    Negative Logits
     glan
    -0.84
     „,
    -0.71
     kram
    -0.71
     Anm
    -0.69
     ohr
    -0.68
     bayern
    -0.67
     sog
    -0.67
     aen
    -0.66
     Münch
    -0.65
     myster
    -0.65
    POSITIVE LOGITS
    municipi
    0.73
    comuna
    0.64
    częściej
    0.59
    strona
    0.59
    sumowanie
    0.58
    nasel
    0.57
    SneakyThrows
    0.55
    Merhaba
    0.53
    település
    0.52
    polski
    0.51
    Activations Density 0.843%

    No Known Activations