© 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. 6-RES-JB
    11. 1729
    Prev
    Next
    INDEX
    Explanations

    specific keywords related to engineering designs or systems that involve containers or containment

    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
    1964
    +0.18
    1.0%
    544
    +0.15
    0.8%
    1233
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1964
    +0.18
    0.02
    1926
    +0.15
    0.02
    438
    +0.12
    0.03
    Negative Logits
     intersper
    -1.91
     apprehen
    -1.62
     encomp
    -1.61
     gaily
    -1.61
     reluct
    -1.59
     reconno
    -1.58
     disagre
    -1.56
     accla
    -1.55
     unspeak
    -1.55
     inconce
    -1.51
    POSITIVE LOGITS
     container
    1.76
     Container
    1.72
    container
    1.71
    Container
    1.63
     containers
    1.60
     Containers
    1.50
    CONTAINER
    1.30
    Containers
    1.24
    TAINER
    1.24
    containers
    1.22
    Activations Density 0.297%

    No Known Activations