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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6737
    Prev
    Next
    INDEX
    Explanations

    words related to freedom and social movements

    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
    1842
    +0.14
    0.4%
    1967
    +0.13
    0.4%
    468
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1116
    +0.14
    0.03
    1856
    +0.13
    0.04
    1842
    +0.11
    0.04
    Negative Logits
     autorytatywna
    -0.69
     utop
    -0.66
     Fürst
    -0.65
     Lombar
    -0.65
     Pfalz
    -0.64
     Heft
    -0.63
     Köl
    -0.62
     NKC
    -0.61
     Donau
    -0.61
     BIBSYS
    -0.61
    POSITIVE LOGITS
    的意思
    0.64
    )
    0.62
     nmax
    0.58
    <bos>
    0.56
     objs
    0.55
     Cauliflower
    0.55
    ),
    0.54
     Strawberries
    0.54
     Asparagus
    0.54
    ).
    0.54
    Activations Density 0.220%

    No Known Activations