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. 15729
    Prev
    Next
    INDEX
    Explanations

    phrases related to confirmation or reporting

    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
    899
    +0.13
    0.4%
    1370
    +0.11
    0.4%
    172
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    899
    +0.13
    0.04
    1370
    +0.11
    0.04
    172
    +0.11
    0.02
    Negative Logits
     utop
    -0.60
    phonse
    -0.59
     etik
    -0.58
     quibus
    -0.57
    erenc
    -0.54
     pels
    -0.53
    AfterEach
    -0.53
     lapto
    -0.53
     suple
    -0.53
     Strukt
    -0.52
    POSITIVE LOGITS
     confirm
    1.04
     confirmed
    1.02
     Confirm
    1.01
     confirmation
    1.01
     Confirmed
    1.01
     confirming
    0.99
     confirmations
    0.97
    confirmed
    0.94
     confirms
    0.94
     Confirmation
    0.93
    Activations Density 0.058%

    No Known Activations