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. 15573
    Prev
    Next
    INDEX
    Explanations

    text related to goals, aspirations, achievements, and reflection

    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
    674
    +0.12
    0.3%
    872
    +0.10
    0.3%
    630
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    38
    +0.12
    0.03
    630
    +0.10
    0.03
    395
    +0.08
    0.04
    Negative Logits
    Vb
    -0.46
    solicited
    -0.44
     configureStore
    -0.42
     JFK
    -0.41
     getResource
    -0.41
    Xc
    -0.40
     severally
    -0.40
    Uf
    -0.39
    Cechy
    -0.39
    Gj
    -0.39
    POSITIVE LOGITS
     CiNii
    0.79
     hecta
    0.70
     CURI
    0.66
     fédé
    0.66
     NKC
    0.66
     lapto
    0.65
     perpé
    0.65
     sembrano
    0.63
     pama
    0.63
     LIRE
    0.63
    Activations Density 0.332%

    No Known Activations