Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7842
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning personal improvement, achievement, and self-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%
    1510
    +0.11
    0.3%
    453
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1510
    +0.12
    0.04
    1919
    +0.11
    0.05
    1114
    +0.08
    0.03
    Negative Logits
     reluct
    -2.32
     disagre
    -2.21
     increa
    -2.17
     indestru
    -2.12
     shenan
    -2.12
     apprehen
    -2.10
     maneu
    -2.06
     encomp
    -2.05
     depic
    -2.02
     philanth
    -1.99
    POSITIVE LOGITS
    FormTagHelper
    0.67
     Paglinawan
    0.67
     getItemId
    0.64
    SerializeField
    0.63
    MetaType
    0.63
     ***!
    0.62
     also
    0.62
     AttributeSet
    0.61
     也
    0.59
    也
    0.59
    Activations Density 0.226%

    No Known Activations