Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15516
    Prev
    Next
    INDEX
    Explanations

    phrases related to job roles and career changes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1166
    +0.07
    0.2%
    197
    +0.07
    0.2%
    1654
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1166
    +0.07
    0.04
    1334
    +0.07
    0.03
    1892
    +0.07
    0.03
    Negative Logits
     majest
    -0.79
     intellig
    -0.76
     gesta
    -0.74
     fers
    -0.73
     barri
    -0.71
     lende
    -0.68
     hek
    -0.65
     bont
    -0.65
     plis
    -0.64
     frans
    -0.64
    POSITIVE LOGITS
     pursue
    0.65
     pamph
    0.51
     pastures
    0.49
     concentrate
    0.49
    Açık
    0.49
     join
    0.48
     greener
    0.47
     devote
    0.47
     appease
    0.47
     pursuing
    0.46
    Activations Density 0.240%

    No Known Activations