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. 14932
    Prev
    Next
    INDEX
    Explanations

    websites or URLs related to a specific organization or community

    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
    131
    +0.16
    0.9%
    1145
    +0.14
    0.8%
    1810
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.16
    0.07
    227
    +0.14
    0.09
    283
    +0.12
    0.00
    Negative Logits
    <bos>
    -1.94
     springfox
    -0.69
     Roskov
    -0.63
     endow
    -0.61
    uesia
    -0.57
     renovate
    -0.57
    washingtonpost
    -0.56
     BigNumberish
    -0.56
     AssemblyCompany
    -0.55
     renew
    -0.55
    POSITIVE LOGITS
     maksi
    1.38
     silikon
    1.27
     panik
    1.25
     kasa
    1.21
     seksi
    1.21
     kafe
    1.21
     kompres
    1.21
     kac
    1.20
     ekos
    1.19
     ekst
    1.15
    Activations Density 0.865%

    No Known Activations