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. 15861
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences, struggles, and communication with others

    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
    1235
    +0.11
    0.3%
    689
    +0.09
    0.3%
    260
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1235
    +0.11
    0.04
    973
    +0.09
    0.02
    298
    +0.08
    0.02
    Negative Logits
     increa
    -1.86
     emphat
    -1.84
     fuf
    -1.83
     maneu
    -1.81
     effe
    -1.80
     milf
    -1.77
     fte
    -1.76
     inev
    -1.76
     thut
    -1.76
     fta
    -1.76
    POSITIVE LOGITS
    <bos>
    0.68
     wanted
    0.66
    ]")]
    0.61
     Roskov
    0.60
    ]))
    
    0.60
     want
    0.59
    enterOuterAlt
    0.58
     gainera
    0.58
    equalTo
    0.58
    "])){
    0.58
    Activations Density 0.199%

    No Known Activations