© 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. 1201
    Prev
    Next
    INDEX
    Explanations

    the term "Sabathia" occurring in a specific context or topic

    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
    1949
    +0.07
    0.2%
    1806
    +0.07
    0.2%
    1860
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.07
    0.04
    1343
    +0.07
    0.08
    1363
    +0.07
    0.05
    Negative Logits
     rootReducer
    -0.62
     kuan
    -0.58
     callBack
    -0.56
     _:
    -0.55
     limestones
    -0.54
     deleteAll
    -0.52
     gracilis
    -0.51
     memberId
    -0.50
    Itens
    -0.49
     picha
    -0.48
    POSITIVE LOGITS
    hia
    1.01
    ISA
    0.90
     halfway
    0.88
    isa
    0.75
     vété
    0.72
    onavir
    0.69
     effe
    0.68
    trás
    0.66
     noël
    0.66
    脚注の使い方
    0.65
    Activations Density 0.456%

    No Known Activations