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. 14895
    Prev
    Next
    INDEX
    Explanations

    negative emotions or situations like bitterness or loss

    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
    1981
    +0.14
    0.6%
    897
    +0.12
    0.5%
    920
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.14
    0.04
    147
    +0.12
    0.03
    1639
    +0.12
    0.03
    Negative Logits
    <bos>
    -2.14
    AppMethodBeat
    -0.91
    Pró
    -0.88
    AutoScale
    -0.85
    SizeMode
    -0.84
    Vegeu
    -0.83
    IsRequired
    -0.82
    AddAttribute
    -0.81
    Desta
    -0.78
    Mapa
    -0.78
    POSITIVE LOGITS
     frankfurt
    2.01
     stockholm
    1.95
    fordable
    1.89
     jaya
    1.84
     dises
    1.80
     munich
    1.79
     wien
    1.76
     squa
    1.76
     bangkok
    1.75
     toledo
    1.74
    Activations Density 0.270%

    No Known Activations