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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 527
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to geographical locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1343
    +0.20
    0.8%
    50
    +0.13
    0.5%
    1842
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.20
    0.14
    1043
    +0.13
    0.09
    227
    +0.12
    0.10
    Negative Logits
    <bos>
    -2.69
     święta
    -0.70
     segíts
    -0.69
     gezwungen
    -0.69
     denounce
    -0.68
     and
    -0.68
    .
    -0.67
     reinstate
    -0.67
     nocy
    -0.67
     to
    -0.66
    POSITIVE LOGITS
     alkoh
    1.77
     keramik
    1.64
     kosme
    1.62
     Kategor
    1.60
     meis
    1.58
     gend
    1.55
     incess
    1.53
     kram
    1.50
     karton
    1.48
     dises
    1.48
    Activations Density 0.740%

    No Known Activations