© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 7088
    Prev
    Next
    INDEX
    Explanations

    names of people, particularly with the name "Mohammed" or variations like "Mohammad" and "Mohamed"

    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
    1480
    +0.10
    0.4%
    50
    +0.10
    0.4%
    1035
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.10
    0.07
    1097
    +0.10
    0.06
    1343
    +0.10
    0.06
    Negative Logits
    <bos>
    -1.89
     Bakar
    -0.71
     Muhamma
    -0.67
     lanka
    -0.66
     Kese
    -0.65
     bayan
    -0.65
     Sya
    -0.64
     nikah
    -0.63
     muna
    -0.61
     Rasul
    -0.60
    POSITIVE LOGITS
     quoique
    1.29
     Mlle
    1.21
     unspeak
    1.18
     indestru
    1.17
     indescri
    1.16
     unlaw
    1.15
     unwarran
    1.14
     affor
    1.13
     beaute
    1.13
     madonna
    1.13
    Activations Density 0.398%

    No Known Activations