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. 1648
    Prev
    Next
    INDEX
    Explanations

    terms related to political and social ideologies, as well as specific names and topics within these fields

    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
    1842
    +0.15
    0.5%
    2033
    +0.10
    0.3%
    1150
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.15
    0.09
    1682
    +0.10
    0.05
    862
    +0.08
    0.02
    Negative Logits
     tinte
    -0.77
     parati
    -0.75
     soggior
    -0.74
     onor
    -0.70
     ridu
    -0.67
     télécharge
    -0.66
     alun
    -0.66
     augus
    -0.65
     allarg
    -0.65
     lomb
    -0.63
    POSITIVE LOGITS
     vainly
    0.86
     shewn
    0.77
     quitted
    0.76
     impelled
    0.76
     unspeak
    0.70
     apprehen
    0.70
     assailed
    0.69
     rejoiced
    0.67
     disagre
    0.67
     shuddered
    0.67
    Activations Density 0.978%

    No Known Activations