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. 2455
    Prev
    Next
    INDEX
    Explanations

    personal names

    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
    1506
    +0.13
    0.7%
    1335
    +0.12
    0.7%
    812
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.13
    0.05
    1335
    +0.12
    0.04
    690
    +0.12
    0.03
    Negative Logits
    <bos>
    -0.86
    ellemző
    -0.70
     roleId
    -0.61
    Další
    -0.59
    Jakie
    -0.56
    Czym
    -0.56
    Dział
    -0.55
    Podob
    -0.52
     transact
    -0.52
    com
    -0.52
    POSITIVE LOGITS
     Jer
    1.48
     JER
    1.40
    Jer
    1.39
     Jeremy
    1.33
    Jeremy
    1.28
     jer
    1.22
    JER
    1.21
    jeremy
    1.07
     kram
    0.96
    jer
    0.92
    Activations Density 0.506%

    No Known Activations