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. 13666
    Prev
    Next
    INDEX
    Explanations

    phrases related to ethical behavior and societal issues

    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
    330
    +0.11
    0.3%
    581
    +0.10
    0.3%
    2036
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    330
    +0.11
    0.04
    1257
    +0.10
    0.04
    1592
    +0.08
    0.04
    Negative Logits
     severally
    -0.55
     Manufact
    -0.54
     pooh
    -0.52
     Righ
    -0.52
     accla
    -0.50
     mew
    -0.50
     snoopy
    -0.50
     philanth
    -0.49
     swee
    -0.48
     Ename
    -0.48
    POSITIVE LOGITS
     whatsoever
    0.98
     nor
    0.67
     except
    0.60
    Saluti
    0.56
     anymore
    0.55
    except
    0.53
     estekak
    0.51
    idać
    0.50
    المشاركات
    0.49
    <bos>
    0.47
    Activations Density 0.326%

    No Known Activations