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. 1457
    Prev
    Next
    INDEX
    Explanations

    words related to personal experiences and explanations

    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
    1108
    +0.11
    0.3%
    674
    +0.11
    0.3%
    175
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    175
    +0.11
    0.07
    586
    +0.11
    0.05
    847
    +0.09
    0.03
    Negative Logits
     reluct
    -1.74
     indestru
    -1.71
     fta
    -1.69
     ?...
    -1.69
     emphat
    -1.69
     strick
    -1.69
     snoopy
    -1.68
     increa
    -1.67
     secon
    -1.66
     disagre
    -1.66
    POSITIVE LOGITS
    <bos>
    1.09
     nonetheless
    1.04
     nevertheless
    0.82
     ändå
    0.75
     anyway
    0.70
     enough
    0.63
     comunque
    0.62
    SystemColors
    0.60
    .
    0.59
     certainly
    0.59
    Activations Density 0.760%

    No Known Activations