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. 15359
    Prev
    Next
    INDEX
    Explanations

    phrases related to self-reflection and introspection

    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
    381
    +0.14
    0.4%
    674
    +0.13
    0.4%
    599
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1
    +0.14
    0.04
    1282
    +0.13
    0.02
    1650
    +0.11
    0.02
    Negative Logits
     Juf
    -1.79
     stockholm
    -1.77
     dises
    -1.69
     lidl
    -1.66
     lyon
    -1.63
     wien
    -1.61
     leonardo
    -1.61
     squa
    -1.59
     frankfurt
    -1.59
     jorge
    -1.58
    POSITIVE LOGITS
    <bos>
    1.35
     definitely
    0.79
     actually
    0.72
     really
    0.71
     my
    0.70
     pretty
    0.70
     probably
    0.69
     very
    0.69
     I
    0.69
     honestly
    0.68
    Activations Density 0.338%

    No Known Activations