© 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. 13278
    Prev
    Next
    INDEX
    Explanations

    occurrences related to legal complaints and initiatives

    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
    +0.17
    0.5%
    1150
    +0.12
    0.4%
    137
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.17
    0.06
    1804
    +0.12
    0.04
    514
    +0.11
    0.02
    Negative Logits
     hairc
    -2.55
     scrat
    -2.31
     affor
    -2.27
     swarovski
    -2.17
     increa
    -2.17
     ecru
    -2.14
     indestru
    -2.14
     embodi
    -2.12
     suscep
    -2.12
     cushi
    -2.11
    POSITIVE LOGITS
    <bos>
    1.16
    copg
    0.73
    smithy
    0.72
     gynhyrchwyd
    0.72
    phosa
    0.71
    fromnode
    0.69
    ніципа
    0.69
     simplifié
    0.67
     <>",
    0.67
    DeleteBehavior
    0.66
    Activations Density 0.280%

    No Known Activations