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. 8200
    Prev
    Next
    INDEX
    Explanations

    mentions of specific entities or organizations mentioned in the text

    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
    478
    +0.13
    0.4%
    1978
    +0.11
    0.3%
    1741
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1984
    +0.13
    0.06
    1654
    +0.11
    0.05
    86
    +0.10
    0.02
    Negative Logits
     ayaa
    -0.78
     umo
    -0.75
     saad
    -0.69
     naer
    -0.68
     karna
    -0.67
     cabrio
    -0.67
     kark
    -0.66
     saha
    -0.65
     hej
    -0.65
     pank
    -0.65
    POSITIVE LOGITS
     itself
    0.51
    Skocz
    0.51
    '
    0.50
    Enregistrer
    0.48
    <bos>
    0.48
    ’
    0.48
     Wtf
    0.46
    uksessa
    0.43
    $'
    0.43
    Xoxo
    0.43
    Activations Density 0.330%

    No Known Activations