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. 1341
    Prev
    Next
    INDEX
    Explanations

    descriptive terms related to actions or behaviors of individuals

    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
    1870
    +0.13
    0.4%
    990
    +0.11
    0.3%
    297
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    990
    +0.13
    0.06
    332
    +0.11
    0.06
    284
    +0.10
    0.07
    Negative Logits
     interessa
    -1.06
    Rgds
    -0.98
     parteci
    -0.97
     dovr
    -0.97
     lancia
    -0.95
     dovre
    -0.95
     trovo
    -0.93
     sappi
    -0.92
     aspetta
    -0.91
     vuol
    -0.90
    POSITIVE LOGITS
     EINVAL
    0.62
    .
    0.59
     are
    0.55
    ünste
    0.52
     vannak
    0.52
     and
    0.52
     HttpHeaders
    0.51
    ,
    0.50
     -
    0.49
    ections
    0.49
    Activations Density 0.393%

    No Known Activations