© 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. 0-RES-JB
    11. 2102
    Prev
    Next
    INDEX
    Explanations

    phrases related to mood and emotions

    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
    805
    +0.09
    0.3%
    1026
    +0.09
    0.3%
    908
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1026
    +0.09
    0.02
    175
    +0.09
    0.02
    1594
    +0.07
    0.02
    Negative Logits
     nõ
    -0.73
     pü
    -0.73
     kaas
    -0.65
     inimes
    -0.65
     meil
    -0.63
     nagu
    -0.63
     mitte
    -0.61
     võimal
    -0.60
    <bos>
    -0.60
     terv
    -0.59
    POSITIVE LOGITS
     mood
    2.90
     Mood
    2.45
     moods
    2.40
    Mood
    2.24
    mood
    2.13
     moody
    1.20
     sappi
    1.18
     affor
    1.17
     maroc
    1.14
     embodi
    1.11
    Activations Density 0.145%

    No Known Activations