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. 13589
    Prev
    Next
    INDEX
    Explanations

    names of historical figures, locations, and organizations, especially related to politics and civil rights

    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
    227
    +0.15
    0.4%
    872
    +0.08
    0.3%
    509
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.15
    0.09
    1957
    +0.08
    0.03
    1291
    +0.08
    0.06
    Negative Logits
     kask
    -1.20
     kram
    -1.19
     karton
    -1.19
     stoff
    -1.17
     traktor
    -1.16
     hek
    -1.16
     plak
    -1.12
     elek
    -1.11
     kade
    -1.10
     palet
    -1.09
    POSITIVE LOGITS
     Áng
    0.76
     Haci
    0.74
     Mónica
    0.73
     Darío
    0.72
     Justo
    0.69
    ⓧ
    0.69
     Whence
    0.69
     Mejía
    0.66
     soumettre
    0.64
     Valentín
    0.63
    Activations Density 0.933%

    No Known Activations