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. 215
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or processes

    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
    1.0%
    324
    +0.09
    0.4%
    507
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    507
    +0.22
    0.08
    92
    +0.09
    0.07
    166
    +0.08
    0.07
    Negative Logits
    <bos>
    -3.01
    ///**
    -0.70
    Filmografie
    -0.64
    ,
    -0.63
    .
    -0.61
     also
    -0.61
    public
    -0.60
    /***
    
    -0.59
     bezeichneter
    -0.58
    private
    -0.58
    POSITIVE LOGITS
     Juf
    1.53
     stockholm
    1.51
     eiffel
    1.46
     madonna
    1.43
     unlaw
    1.43
     toledo
    1.42
     squa
    1.41
     sovere
    1.41
     affor
    1.38
     unwarran
    1.36
    Activations Density 1.724%

    No Known Activations