© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 127
    Prev
    Next
    INDEX
    Explanations

    words related to entertainment and performances

    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
    528
    +0.10
    0.3%
    1926
    +0.09
    0.3%
    423
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.10
    0.04
    283
    +0.09
    0.01
    690
    +0.08
    0.05
    Negative Logits
     McLaugh
    -1.32
     intersper
    -1.26
     Wtf
    -1.14
     encomp
    -1.12
     disambigu
    -1.03
     depic
    -0.92
     quitted
    -0.92
     apprehen
    -0.92
     McInt
    -0.92
     disagre
    -0.91
    POSITIVE LOGITS
    tainment
    2.00
    tainer
    1.27
    TAINMENT
    1.16
    tainers
    1.12
    taining
    1.06
    tained
    1.03
    tain
    1.00
     Baillargeon
    0.93
    tains
    0.90
    tainable
    0.82
    Activations Density 0.372%

    No Known Activations