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. 204
    Prev
    Next
    INDEX
    Explanations

    locations or addresses, such as street names and cities

    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
    +0.14
    0.5%
    481
    +0.07
    0.3%
    1092
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1487
    +0.14
    0.02
    1498
    +0.07
    0.02
    702
    +0.07
    0.02
    Negative Logits
    <bos>
    -1.97
    ///**
    -0.58
    ždý
    -0.56
    intios
    -0.56
    },[])
    -0.55
    glBind
    -0.52
    /***
    
    -0.52
    lateinit
    -0.52
    //{
    
    -0.51
    TestBed
    -0.50
    POSITIVE LOGITS
     affor
    1.08
     stockholm
    1.05
     perfet
    1.02
     maneu
    1.00
     nece
    0.96
     guarante
    0.96
     budapest
    0.95
     effe
    0.93
     fortn
    0.93
     nomine
    0.92
    Activations Density 0.030%

    No Known Activations