© 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. 4251
    Prev
    Next
    INDEX
    Explanations

    words related to the succession or replacement of individuals in a specific role or position

    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
    1407
    +0.14
    0.6%
    1035
    +0.11
    0.4%
    1127
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1035
    +0.14
    0.03
    757
    +0.11
    0.03
    1407
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.09
    public
    -0.77
    about
    -0.73
    /*
    -0.73
     about
    -0.72
    {/*
    -0.71
    wrap
    -0.71
    mail
    -0.71
    base
    -0.70
    frac
    -0.70
    POSITIVE LOGITS
     affor
    2.45
     milf
    2.12
     increa
    2.12
     reluct
    2.07
     stockholm
    2.06
     strick
    2.03
     shenan
    2.03
     hairc
    2.02
     snoopy
    2.01
     peppa
    1.99
    Activations Density 0.325%

    No Known Activations