© 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. 12635
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to criminal intent and actions

    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
    394
    +0.08
    0.2%
    1553
    +0.08
    0.2%
    1004
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    100
    +0.08
    0.04
    1004
    +0.08
    0.04
    972
    +0.08
    0.03
    Negative Logits
     Anm
    -0.71
     gmbh
    -0.63
     ankara
    -0.60
     mef
    -0.58
     impractica
    -0.58
     Oester
    -0.58
     gend
    -0.57
     haer
    -0.57
     Pende
    -0.56
     vost
    -0.56
    POSITIVE LOGITS
     intent
    0.61
     intentional
    0.58
     referenties
    0.57
    intent
    0.56
    FailureListener
    0.54
     intention
    0.52
     provare
    0.51
     smtplib
    0.51
     deliberate
    0.51
    FTFY
    0.50
    Activations Density 0.439%

    No Known Activations