© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12825
    Prev
    Next
    INDEX
    Explanations

    phrases related to getting away with unethical behavior or crimes

    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
    674
    +0.13
    0.4%
    788
    +0.10
    0.3%
    604
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    788
    +0.13
    0.04
    1424
    +0.10
    0.04
    1475
    +0.09
    0.03
    Negative Logits
    <^
    -0.54
    :,,
    -0.53
     kyo
    -0.53
     apprehen
    -0.52
     Minang
    -0.52
     rêver
    -0.52
     hés
    -0.50
     finit
    -0.50
     berea
    -0.50
     Cik
    -0.50
    POSITIVE LOGITS
     impunity
    0.98
     unchecked
    0.60
    noinspection
    0.55
    actionMode
    0.53
     undetected
    0.52
     unrestricted
    0.48
    runApp
    0.48
     untreated
    0.47
     fritt
    0.47
     freely
    0.44
    Activations Density 0.519%

    No Known Activations