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. 576
    Prev
    Next
    INDEX
    Explanations

    words related to rambling or long-winded speech

    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
    1137
    +0.14
    0.6%
    690
    +0.13
    0.5%
    36
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.14
    0.07
    1363
    +0.13
    0.06
    1013
    +0.11
    0.07
    Negative Logits
    <bos>
    -1.92
    Vegeu
    -0.71
    contentLoaded
    -0.68
    /***
    
    -0.67
    maxcdn
    -0.67
    glEnd
    -0.67
     contact
    -0.66
    displayquote
    -0.66
    join
    -0.66
    Erreferentziak
    -0.66
    POSITIVE LOGITS
     swarovski
    1.71
     unce
    1.65
     unden
    1.57
     friable
    1.56
     oleo
    1.55
     stockholm
    1.55
     sovere
    1.53
     ecru
    1.53
     madonna
    1.51
     impra
    1.51
    Activations Density 0.618%

    No Known Activations