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. 2821
    Prev
    Next
    INDEX
    Explanations

    serious or negative situations or events, particularly with a sense of gloom

    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
    1609
    +0.10
    0.3%
    147
    +0.10
    0.3%
    204
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    147
    +0.10
    0.03
    1609
    +0.10
    0.04
    1931
    +0.09
    0.04
    Negative Logits
     vasi
    -0.63
     bont
    -0.56
     stoff
    -0.56
     tenda
    -0.55
     higien
    -0.53
     augus
    -0.53
     tyn
    -0.53
     tait
    -0.51
     karton
    -0.51
     lemp
    -0.50
    POSITIVE LOGITS
     bleak
    0.68
     grim
    0.66
     gloom
    0.65
     gloomy
    0.65
     somber
    0.62
     pessimistic
    0.59
     schoolmaster
    0.59
     pessimism
    0.59
     soldati
    0.58
     tidings
    0.55
    Activations Density 0.341%

    No Known Activations