© 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. 1930
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving up things or abandoning something

    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
    1044
    +0.14
    0.4%
    1166
    +0.12
    0.4%
    1962
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1166
    +0.14
    0.03
    1962
    +0.12
    0.03
    1044
    +0.10
    0.03
    Negative Logits
     sappi
    -0.85
     lidl
    -0.85
     wald
    -0.84
     malay
    -0.83
     wherea
    -0.81
     Hano
    -0.81
     effe
    -0.81
     bangkok
    -0.79
     Hez
    -0.76
     michelin
    -0.76
    POSITIVE LOGITS
     surrender
    0.54
    <bos>
    0.52
     relinquish
    0.49
     surrendered
    0.49
    放弃
    0.48
    ьаж
    0.47
    EDEFAULT
    0.47
     abandon
    0.46
     possession
    0.45
     surrendering
    0.45
    Activations Density 0.092%

    No Known Activations