© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 365
    Prev
    Next
    INDEX
    Explanations

    expressions related to emotions and relationships, particularly love and gratitude

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    303
    +0.07
    0.2%
    1100
    +0.06
    0.2%
    82
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.07
    0.02
    1385
    +0.06
    0.03
    1137
    +0.06
    0.03
    Negative Logits
    ⓧ
    -0.97
    <bos>
    -0.86
    LEncoder
    -0.71
    <?
    -0.70
    memoized
    -0.70
    EndContext
    -0.68
    TargetException
    -0.68
    Về
    -0.67
    execSQL
    -0.67
    </thead>
    -0.66
    POSITIVE LOGITS
     affor
    1.73
     impra
    1.63
     quoique
    1.62
     increa
    1.58
     maneu
    1.58
     wherea
    1.56
     strick
    1.56
     guarante
    1.52
     Juf
    1.49
     shenan
    1.45
    Activations Density 0.257%

    No Known Activations