© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3559
    Prev
    Next
    INDEX
    Explanations

    phrases related to social and political issues

    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
    1343
    +0.14
    0.4%
    50
    +0.10
    0.3%
    1967
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1725
    +0.14
    0.02
    1510
    +0.10
    0.03
    177
    +0.09
    0.03
    Negative Logits
     gaily
    -1.04
     disagre
    -0.99
     tolerably
    -0.90
     vainly
    -0.88
     increa
    -0.86
     reluct
    -0.85
     withal
    -0.84
     milf
    -0.84
     apprehen
    -0.83
     encomp
    -0.82
    POSITIVE LOGITS
    cassert
    0.62
    Contactez
    0.60
    stdbool
    0.58
    Zapraszamy
    0.56
    pří
    0.56
     scopri
    0.55
     sembrano
    0.52
    stdarg
    0.51
    cstdlib
    0.51
    jednoc
    0.48
    Activations Density 0.498%

    No Known Activations