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. 113
    Prev
    Next
    INDEX
    Explanations

    names of a person named Alan

    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
    331
    +0.15
    0.8%
    31
    +0.15
    0.8%
    313
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.15
    0.05
    1741
    +0.15
    -0.00
    227
    +0.14
    0.06
    Negative Logits
     darted
    -0.67
     strode
    -0.66
     intersper
    -0.60
     shuddered
    -0.58
     Sinon
    -0.56
     Parce
    -0.55
     sobbed
    -0.55
    Suka
    -0.55
    NameInMap
    -0.55
    principalTable
    -0.53
    POSITIVE LOGITS
     Alan
    0.89
    Alan
    0.85
     ALAN
    0.68
    ALAN
    0.66
     Berber
    0.65
     Magh
    0.61
     maroc
    0.59
     alan
    0.58
    occan
    0.57
     maroca
    0.55
    Activations Density 0.636%

    No Known Activations