© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 7968
    Prev
    Next
    INDEX
    Explanations

    words related to romantic settings or activities, particularly associated with Valentine's Day

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1103
    +0.15
    0.7%
    50
    +0.14
    0.7%
    1276
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1872
    +0.15
    0.03
    1276
    +0.14
    0.03
    1103
    +0.13
    0.03
    Negative Logits
    <bos>
    -2.76
    mergeFrom
    -0.76
    {{--
    -0.75
    AsUp
    -0.71
    AutoScale
    -0.71
    |=\
    -0.71
    modelBuilder
    -0.71
    CreateIndex
    -0.71
    SequentialGroup
    -0.70
    WebControls
    -0.70
    POSITIVE LOGITS
     impra
    2.21
     maneu
    2.19
     scrat
    2.13
     reluct
    2.11
     increa
    2.05
     strick
    2.04
     affor
    2.03
     unden
    1.95
     excru
    1.94
     indestru
    1.92
    Activations Density 0.159%

    No Known Activations