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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 8242
    Prev
    Next
    INDEX
    Explanations

    phrases related to outdoor spaces and fields

    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
    168
    +0.14
    0.6%
    2004
    +0.14
    0.6%
    650
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.14
    0.03
    650
    +0.14
    0.03
    2004
    +0.14
    0.03
    Negative Logits
    RTSN
    -0.53
    glPushMatrix
    -0.50
     Chbosky
    -0.48
     harmonie
    -0.48
     nueces
    -0.47
    騨
    -0.45
    twimg
    -0.45
    AutoScaleMode
    -0.45
    bootstrapcdn
    -0.44
     PackageManager
    -0.43
    POSITIVE LOGITS
     field
    1.34
     Field
    1.30
    field
    1.28
     FIELD
    1.21
    Field
    1.21
     fields
    1.15
     Fields
    1.11
    FIELD
    1.10
    fields
    1.10
    Fields
    0.97
    Activations Density 0.083%

    No Known Activations