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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1126
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbs related to uncertainty and mystery

    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
    1525
    +0.08
    0.2%
    872
    +0.07
    0.2%
    655
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1525
    +0.08
    0.04
    1615
    +0.07
    0.06
    2044
    +0.07
    0.07
    Negative Logits
     Luglio
    -0.77
     mikrofon
    -0.73
     kompati
    -0.69
     silikon
    -0.67
     koncentr
    -0.67
     Settembre
    -0.67
     Giugno
    -0.66
     numé
    -0.66
     Juf
    -0.65
     higien
    -0.65
    POSITIVE LOGITS
     unpredictable
    0.91
     unpredic
    0.89
     uncertainty
    0.84
     confuse
    0.78
     confusing
    0.77
     confuses
    0.76
     ambiguity
    0.76
     uncertain
    0.74
     complicate
    0.71
     ambiguous
    0.70
    Activations Density 0.741%

    No Known Activations