© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14264
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and reflections

    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
    172
    +0.11
    0.3%
    1105
    +0.10
    0.3%
    674
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.11
    0.03
    1105
    +0.10
    0.04
    855
    +0.09
    0.04
    Negative Logits
     unspeak
    -0.93
     increa
    -0.90
     shenan
    -0.89
     indescri
    -0.86
     depic
    -0.84
     alre
    -0.83
     attemp
    -0.82
     emphat
    -0.81
     exorbit
    -0.80
     affor
    -0.80
    POSITIVE LOGITS
     leave
    0.99
     left
    0.91
    leave
    0.89
     leaving
    0.88
     Leave
    0.85
     LEAVE
    0.82
    Leave
    0.82
     leaves
    0.79
    Leaving
    0.73
    Left
    0.73
    Activations Density 0.166%

    No Known Activations