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. 15455
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue in first-person recounting of personal experiences

    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
    1150
    +0.17
    0.5%
    184
    +0.13
    0.4%
    1535
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.17
    0.07
    382
    +0.13
    0.06
    1533
    +0.12
    0.02
    Negative Logits
     bandung
    -1.34
     nece
    -1.28
     muna
    -1.25
     emphat
    -1.23
     embodi
    -1.20
     effe
    -1.20
     guarante
    -1.19
     ?...
    -1.19
     inev
    -1.17
     wherea
    -1.16
    POSITIVE LOGITS
     Then
    0.87
     then
    0.81
    then
    0.74
    Then
    0.73
     he
    0.69
     He
    0.65
     so
    0.65
     Later
    0.63
     So
    0.62
    FailureListener
    0.62
    Activations Density 0.481%

    No Known Activations