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. 3031
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "also," but it also appears to target specific informational details from varied content sources

    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
    172
    +0.16
    0.6%
    645
    +0.13
    0.5%
    228
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.16
    0.08
    645
    +0.13
    0.07
    228
    +0.13
    0.06
    Negative Logits
     karton
    -0.88
     utop
    -0.78
     sement
    -0.77
     territo
    -0.76
     hunde
    -0.74
     silikon
    -0.73
     lemp
    -0.71
     solidar
    -0.71
     kosme
    -0.70
     keramik
    -0.69
    POSITIVE LOGITS
    also
    0.80
     also
    0.78
     ALSO
    0.71
    también
    0.67
    Also
    0.66
     também
    0.65
     Also
    0.62
     también
    0.62
     også
    0.60
     juga
    0.59
    Activations Density 0.251%

    No Known Activations