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. 15739
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to security and technology, especially in the context of setting up secure processes and devices like wallets or power plants

    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
    1150
    +0.11
    0.3%
    2034
    +0.09
    0.2%
    1385
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    270
    +0.11
    0.05
    44
    +0.09
    0.03
    1734
    +0.08
    0.04
    Negative Logits
     philanth
    -1.76
     emphat
    -1.76
     volunte
    -1.74
     reluct
    -1.73
     increa
    -1.67
     impra
    -1.67
     accla
    -1.67
     depic
    -1.66
     inev
    -1.66
     encomp
    -1.66
    POSITIVE LOGITS
     whatsoever
    0.92
     nor
    0.87
    <bos>
    0.86
     except
    0.82
    except
    0.81
     anymore
    0.77
     sondern
    0.72
    paddingVertical
    0.68
    marginVertical
    0.66
     or
    0.63
    Activations Density 0.426%

    No Known Activations