© 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. 3437
    Prev
    Next
    INDEX
    Explanations

    the word "salt" in the text

    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
    544
    +0.16
    0.6%
    1387
    +0.11
    0.4%
    67
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    544
    +0.16
    0.03
    1387
    +0.11
    0.02
    67
    +0.11
    0.02
    Negative Logits
    躇
    -0.64
     Micho
    -0.61
     Sequo
    -0.59
     categoryId
    -0.58
     roleId
    -0.57
     Oberlin
    -0.52
     memberId
    -0.51
     requestId
    -0.51
     createDate
    -0.49
     userEmail
    -0.49
    POSITIVE LOGITS
     salt
    1.54
     Salt
    1.50
    salt
    1.47
    Salt
    1.47
     SALT
    1.33
     salts
    1.20
    SALT
    1.13
     Salts
    0.90
     salty
    0.90
     salted
    0.89
    Activations Density 0.060%

    No Known Activations