© 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. 4530
    Prev
    Next
    INDEX
    Explanations

    emotional expressions involving physical touch, particularly hugs

    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
    25
    +0.14
    0.6%
    1101
    +0.11
    0.5%
    228
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.14
    0.04
    1013
    +0.11
    0.04
    25
    +0.11
    0.03
    Negative Logits
    <bos>
    -1.61
    Đi
    -0.64
    ComponentModel
    -0.64
    HasIndex
    -0.63
    CodeDom
    -0.62
    Alemania
    -0.62
    FlatAppearance
    -0.62
    Datuak
    -0.62
    İstinadlar
    -0.60
    Vegeu
    -0.60
    POSITIVE LOGITS
     impra
    1.53
     embra
    1.46
     impractica
    1.35
     strick
    1.33
     stockholm
    1.32
     madonna
    1.29
     desir
    1.26
     fta
    1.25
     unce
    1.24
     disagre
    1.23
    Activations Density 0.524%

    No Known Activations