© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7531
    Prev
    Next
    INDEX
    Explanations

    Boolean variables related to order shipment status

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    programming code snippets or structures related to boolean logic and state.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @shantanudarveshi
    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
    876
    +0.12
    0.3%
    919
    +0.10
    0.3%
    1699
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    919
    +0.12
    0.02
    876
    +0.10
    -0.00
    1216
    +0.09
    0.03
    Negative Logits
     Strukt
    -0.58
    InstrumentedTest
    -0.54
     abstrak
    -0.53
     radikal
    -0.53
    ioutil
    -0.52
    MarshalTo
    -0.50
     konkre
    -0.49
     akade
    -0.49
     kemer
    -0.49
     Kalifor
    -0.48
    POSITIVE LOGITS
     BOOLEAN
    0.81
     ducati
    0.76
     TRUE
    0.72
    BooleanField
    0.71
     assolu
    0.69
     true
    0.69
    false
    0.69
     false
    0.68
     cabrio
    0.68
     napoli
    0.67
    Activations Density 0.139%

    No Known Activations