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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4806
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to societal or ethical issues

    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
    604
    +0.18
    0.5%
    764
    +0.10
    0.3%
    1533
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    96
    +0.18
    0.01
    1531
    +0.10
    0.04
    1958
    +0.09
    0.04
    Negative Logits
    <bos>
    -1.27
     déchir
    -0.68
     reluct
    -0.65
     apprehen
    -0.65
     enlight
    -0.64
     disagre
    -0.63
     Miscell
    -0.62
     keramik
    -0.62
     unspeak
    -0.62
     sophistic
    -0.61
    POSITIVE LOGITS
    municipi
    0.66
    astéro
    0.62
    asteroide
    0.61
    ENODEV
    0.61
     teflon
    0.60
     waisted
    0.60
     rudder
    0.59
    Cześć
    0.58
    onFailure
    0.58
    Obrigada
    0.57
    Activations Density 0.420%

    No Known Activations