© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14245
    Prev
    Next
    INDEX
    Explanations

    references to anniversaries

    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
    776
    +0.15
    0.5%
    1013
    +0.12
    0.4%
    783
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    783
    +0.15
    0.02
    776
    +0.12
    0.02
    48
    +0.11
    0.02
    Negative Logits
     abnorm
    -0.81
     huma
    -0.79
     utop
    -0.78
     unlaw
    -0.73
     BIBSYS
    -0.72
     Departement
    -0.71
     estrema
    -0.71
     chiare
    -0.71
     banan
    -0.70
     umo
    -0.69
    POSITIVE LOGITS
     anniversary
    1.28
    anniversary
    1.20
     Anniversary
    1.08
     anniversaries
    1.03
     celebrations
    0.83
     celebration
    0.82
    Anni
    0.73
     milestone
    0.65
    <bos>
    0.65
    versary
    0.65
    Activations Density 0.064%

    No Known Activations