© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 1761
    Prev
    Next
    INDEX
    Explanations

    references to animation or animated content

    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
    486
    +0.08
    0.3%
    1472
    +0.08
    0.3%
    1872
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    329
    +0.08
    0.03
    1432
    +0.08
    0.02
    1872
    +0.07
    0.03
    Negative Logits
    <bos>
    -0.83
    HostException
    -0.79
    resizeMode
    -0.68
    SafeAreaView
    -0.62
    public
    -0.61
    <?
    -0.60
    squareup
    -0.60
    ੱਚ
    -0.60
    MetaType
    -0.60
    TODOS
    -0.60
    POSITIVE LOGITS
     animation
    2.37
     animating
    2.16
     animations
    2.14
     Animations
    2.13
     animated
    2.07
     Animation
    2.03
     ANIM
    2.00
     anim
    1.96
     animé
    1.93
     animate
    1.89
    Activations Density 0.159%

    No Known Activations