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. 14610
    Prev
    Next
    INDEX
    Explanations

    contact information details, such as phone numbers and addresses

    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
    1334
    +0.20
    1.0%
    1023
    +0.14
    0.7%
    228
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1334
    +0.20
    0.04
    1350
    +0.14
    0.04
    1971
    +0.13
    0.04
    Negative Logits
    <bos>
    -1.50
     intersper
    -0.85
    /**
    -0.74
     disbur
    -0.72
     shuddered
    -0.67
    <?
    -0.66
     darted
    -0.62
    /***
    
    -0.59
     shivered
    -0.59
     vainly
    -0.59
    POSITIVE LOGITS
     Tol
    0.81
     Tow
    0.77
     TOL
    0.76
    TO
    0.75
    TOL
    0.75
     Toe
    0.74
     TO
    0.74
    tolerance
    0.73
    olerance
    0.72
    Tow
    0.71
    Activations Density 0.393%

    No Known Activations