© 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. 6-RES-JB
    11. 4357
    Prev
    Next
    INDEX
    Explanations

    information related to customer service policies, satisfaction guarantees, returns, and exchanges offered by a company

    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
    50
    +0.31
    1.2%
    453
    +0.08
    0.3%
    1531
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1531
    +0.31
    0.05
    873
    +0.08
    0.06
    1088
    +0.08
    0.05
    Negative Logits
    <bos>
    -1.89
     disbur
    -0.61
     abstra
    -0.59
    <tfoot>
    -0.57
     mobilize
    -0.52
    GroupLayout
    -0.51
    },{
    -0.51
    ///**
    -0.50
    afterEach
    -0.50
     defray
    -0.50
    POSITIVE LOGITS
     véhic
    0.86
     jawa
    0.84
     réput
    0.84
     Minang
    0.83
     typique
    0.81
     spécialisé
    0.81
     pleins
    0.81
     bandung
    0.79
     animés
    0.79
     expérimentés
    0.78
    Activations Density 0.529%

    No Known Activations