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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12742
    Prev
    Next
    INDEX
    Explanations

    phrases related to project phases or stages

    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
    1705
    +0.14
    0.5%
    687
    +0.13
    0.5%
    1870
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1705
    +0.14
    0.02
    1950
    +0.13
    0.02
    687
    +0.12
    0.02
    Negative Logits
     ProtoMessage
    -0.50
     sull
    -0.49
    mir
    -0.48
     Mir
    -0.48
     Bieber
    -0.46
     uLocal
    -0.45
     mir
    -0.44
    BufferException
    -0.43
    istoitu
    -0.43
    拮
    -0.42
    POSITIVE LOGITS
     phase
    1.28
    phase
    1.19
     PHASE
    1.19
     Phase
    1.18
    Phase
    1.18
     phases
    1.12
    phases
    1.08
    PHASE
    1.07
     Phases
    1.04
     phased
    1.02
    Activations Density 0.044%

    No Known Activations