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. 8223
    Prev
    Next
    INDEX
    Explanations

    quotes or phrases containing the words "In other words"

    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
    75
    +0.10
    0.3%
    872
    +0.10
    0.3%
    1129
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    62
    +0.10
    0.02
    75
    +0.10
    0.02
    569
    +0.09
    0.03
    Negative Logits
     suspic
    -1.28
     embra
    -1.27
     nece
    -1.20
     fuf
    -1.20
     fasc
    -1.19
     dispen
    -1.17
     inev
    -1.16
     secon
    -1.15
     pessi
    -1.14
     ftu
    -1.13
    POSITIVE LOGITS
    :
    0.56
    obacz
    0.53
    зульта
    0.53
     tört
    0.52
    riction
    0.51
     words
    0.51
     szól
    0.51
     hoffe
    0.51
     alá
    0.50
     palabras
    0.50
    Activations Density 0.093%

    No Known Activations