Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15246
    Prev
    Next
    INDEX
    Explanations

    advice or information related to improving chances of conceiving a specific gender through dietary and pH balance modifications

    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
    478
    +0.11
    0.3%
    283
    +0.09
    0.3%
    1480
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    684
    +0.11
    0.02
    1340
    +0.09
    0.02
    1445
    +0.09
    0.02
    Negative Logits
    <bos>
    -1.94
     vœ
    -0.93
    Výhody
    -0.89
     Jusqu
    -0.88
     HARR
    -0.83
     tiennent
    -0.83
     autorité
    -0.81
    Pře
    -0.81
     scrat
    -0.81
     Ceux
    -0.80
    POSITIVE LOGITS
     ananas
    0.82
     ados
    0.61
    formación
    0.61
     kade
    0.60
    issime
    0.60
     ileg
    0.59
     sinistro
    0.59
     ajustable
    0.58
     raso
    0.58
     intest
    0.58
    Activations Density 0.030%

    No Known Activations