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. 15202
    Prev
    Next
    INDEX
    Explanations

    personal thoughts and emotions expressed in a somewhat scattered and disjointed manner

    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
    674
    +0.23
    3.3%
    108
    +0.03
    0.4%
    876
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    674
    +0.23
    0.05
    1523
    +0.03
    0.18
    108
    +0.03
    0.20
    Negative Logits
     massacres
    -1.02
     disinformation
    -0.96
     atrocities
    -0.95
     traitors
    -0.94
     so
    -0.94
     bombings
    -0.94
     also
    -0.94
     mismanagement
    -0.93
     insurgents
    -0.93
    ,
    -0.91
    POSITIVE LOGITS
    <bos>
    16.48
     dispen
    2.81
    expandindo
    2.79
    GEBURTSDATUM
    2.77
     betweenstory
    2.64
     Administrativna
    2.55
    Autoritní
    2.51
     effe
    2.48
    تقاوى
    2.48
     !...
    2.46
    Activations Density 0.173%

    No Known Activations