© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7163
    Prev
    Next
    INDEX
    Explanations

    words related to survival and life-changing experiences

    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
    1531
    +0.07
    0.2%
    733
    +0.06
    0.2%
    1352
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1497
    +0.07
    0.02
    842
    +0.06
    0.03
    741
    +0.06
    0.03
    Negative Logits
     reluct
    -2.10
     affor
    -2.01
     encomp
    -1.98
     depic
    -1.98
     increa
    -1.96
     shenan
    -1.89
     disagre
    -1.89
     maneu
    -1.88
     impra
    -1.85
     apprehen
    -1.84
    POSITIVE LOGITS
     Exacts
    0.76
     reminder
    0.68
    ynb
    0.66
    WireFormat
    0.66
    writeFieldEnd
    0.66
     reminded
    0.65
    XtraGrid
    0.64
     확인함
    0.63
     الاطلاع
    0.63
     realize
    0.62
    Activations Density 0.378%

    No Known Activations