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. 844
    Prev
    Next
    INDEX
    Explanations

    information related to hunting, hunting gear, and hunting activities

    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
    50
    +0.15
    0.9%
    1994
    +0.13
    0.8%
    411
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1059
    +0.15
    0.03
    1994
    +0.13
    0.02
    559
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.81
     AssemblyCompany
    -0.79
    SystemColors
    -0.73
    芒
    -0.73
    fvar
    -0.71
    AddWithValue
    -0.71
    section
    -0.71
    consulté
    -0.71
    core
    -0.71
    InputBorder
    -0.71
    POSITIVE LOGITS
     indestru
    2.19
     increa
    2.18
     maneu
    2.15
     depic
    2.09
     inev
    2.07
     scrat
    2.06
     accla
    2.05
     impra
    2.05
     reluct
    2.05
     shenan
    2.03
    Activations Density 0.116%

    No Known Activations