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. 1559
    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
    776
    +0.10
    0.3%
    50
    +0.10
    0.3%
    845
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    504
    +0.10
    0.04
    1533
    +0.10
    0.01
    845
    +0.08
    0.02
    Negative Logits
     maksi
    -0.83
     recev
    -0.76
     Keny
    -0.76
    timately
    -0.75
     vettoriale
    -0.70
     sopr
    -0.68
     évit
    -0.66
     azzurro
    -0.66
     seksi
    -0.66
     keramik
    -0.66
    POSITIVE LOGITS
     sort
    0.50
    atguigu
    0.49
    spesies
    0.48
    cassert
    0.46
    كتوبر
    0.45
     maybe
    0.43
    пиона
    0.43
    gelopen
    0.43
     hashlib
    0.42
    frase
    0.42
    Activations Density 0.309%

    No Known Activations