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. 8145
    Prev
    Next
    INDEX
    Explanations

    descriptions or memories related to a person's childhood experiences and nostalgic recollections

    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
    50
    +0.23
    0.9%
    297
    +0.11
    0.4%
    1013
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1410
    +0.23
    0.05
    1469
    +0.11
    0.05
    825
    +0.11
    0.06
    Negative Logits
    <bos>
    -1.87
    displayquote
    -0.70
     serve
    -0.70
    enumerate
    -0.69
     continue
    -0.68
    ///
    -0.67
    @
    -0.66
    HasIndex
    -0.66
    createQuery
    -0.65
    /**
    -0.65
    POSITIVE LOGITS
     guarante
    1.94
     maneu
    1.91
     ftu
    1.85
     Juf
    1.85
     madonna
    1.84
     stockholm
    1.83
     increa
    1.82
     desir
    1.78
     accla
    1.77
     reft
    1.76
    Activations Density 0.809%

    No Known Activations