© 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. 12755
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal activities like breaking into a house or murder cases

    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
    946
    +0.12
    0.3%
    1013
    +0.10
    0.3%
    1842
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.12
    0.07
    100
    +0.10
    0.04
    1461
    +0.09
    0.04
    Negative Logits
     effe
    -0.98
     michelin
    -0.96
     lidl
    -0.93
     affor
    -0.90
     purcha
    -0.90
     nece
    -0.89
     imposs
    -0.88
     guarante
    -0.88
     scrat
    -0.88
     autob
    -0.86
    POSITIVE LOGITS
     Système
    0.51
     confidential
    0.50
     steal
    0.48
     stole
    0.45
    usermodel
    0.44
     offices
    0.44
    prepareStatement
    0.42
    ؤية
    0.42
     burglary
    0.42
     stolen
    0.42
    Activations Density 0.392%

    No Known Activations