© 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. 4215
    Prev
    Next
    INDEX
    Explanations

    phrases related to withdrawing or stepping back from 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
    1328
    +0.15
    0.5%
    860
    +0.14
    0.5%
    899
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    860
    +0.15
    0.03
    1328
    +0.14
    0.03
    1708
    +0.10
    0.02
    Negative Logits
     affor
    -1.20
     reluct
    -1.14
     fortn
    -1.12
     volunte
    -1.08
     snoopy
    -1.08
     increa
    -1.07
     strick
    -1.05
     guarante
    -1.04
     unden
    -1.03
     impra
    -1.02
    POSITIVE LOGITS
     withdraw
    1.17
     withdrawal
    1.14
     withdrawn
    1.12
     withdrew
    1.04
     Withdrawal
    0.95
    withdraw
    0.95
     withdrawing
    0.95
     withdrawals
    0.92
     Withdraw
    0.90
    Withdraw
    0.85
    Activations Density 0.074%

    No Known Activations