© 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. 1612
    Prev
    Next
    INDEX
    Explanations

    exclamatory phrases expressing extreme positivity or enthusiasm

    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
    690
    +0.09
    0.3%
    897
    +0.08
    0.3%
    528
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.09
    0.05
    690
    +0.08
    0.07
    1577
    +0.08
    0.06
    Negative Logits
     may
    -0.95
     do
    -0.93
     can
    -0.92
     will
    -0.91
     also
    -0.91
     continue
    -0.89
    public
    -0.87
     let
    -0.87
     don
    -0.87
     plan
    -0.86
    POSITIVE LOGITS
     affor
    3.61
     increa
    3.41
     impra
    3.37
     scrat
    3.26
     maneu
    3.19
     hairc
    3.00
     stockholm
    3.00
     ecru
    2.99
     michelin
    2.99
     perfet
    2.96
    Activations Density 0.612%

    No Known Activations