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. 8181
    Prev
    Next
    INDEX
    Explanations

    family relationships like in-laws such as siblings-in-law or parents-in-law

    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
    +0.22
    0.8%
    1535
    +0.07
    0.3%
    553
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.22
    0.02
    1913
    +0.07
    0.02
    1375
    +0.07
    0.02
    Negative Logits
    <bos>
    -1.91
    /**
    -0.82
    ⓧ
    -0.73
     mobilize
    -0.65
     expel
    -0.63
     inaugurate
    -0.63
     disbur
    -0.61
    /*
    -0.61
     abolish
    -0.60
     springfox
    -0.60
    POSITIVE LOGITS
     véhic
    1.04
     applau
    0.99
     tén
    0.95
     prét
    0.94
     pleins
    0.94
     paradiso
    0.93
     délib
    0.92
     maroc
    0.92
     ados
    0.92
     Décembre
    0.91
    Activations Density 0.036%

    No Known Activations