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. 5297
    Prev
    Next
    INDEX
    Explanations

    dates expressed as January 8th

    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
    1909
    +0.18
    0.9%
    406
    +0.15
    0.8%
    1262
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1023
    +0.18
    0.07
    1909
    +0.15
    0.06
    517
    +0.15
    0.05
    Negative Logits
    <bos>
    -2.86
    has
    -0.76
    Diwedd
    -0.75
    sky
    -0.73
    lateinit
    -0.70
    public
    -0.70
    Sky
    -0.69
    config
    -0.68
    doc
    -0.68
    x
    -0.67
    POSITIVE LOGITS
     emphat
    2.03
     affor
    1.98
     shenan
    1.97
     unlaw
    1.91
     disagre
    1.90
     excru
    1.87
     impractica
    1.87
     increa
    1.86
     practition
    1.85
     guarante
    1.84
    Activations Density 0.264%

    No Known Activations