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. 2485
    Prev
    Next
    INDEX
    Explanations

    mean-spirited or aggressive language and behavior

    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
    1387
    +0.16
    0.8%
    68
    +0.15
    0.7%
    1491
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    732
    +0.16
    0.03
    1233
    +0.15
    0.04
    1387
    +0.14
    0.03
    Negative Logits
    <bos>
    -1.32
    าสตร์
    -0.74
     للاسماء
    -0.73
    HasColumnType
    -0.71
    Dichlorobenzene
    -0.61
    UseVisualStyle
    -0.61
    CreateMap
    -0.60
     Kitts
    -0.60
    LOYEES
    -0.60
    ConverterFactory
    -0.59
    POSITIVE LOGITS
     milano
    1.38
     frankfurt
    1.38
     sappi
    1.34
     olx
    1.32
     javier
    1.31
     jorge
    1.30
     tramont
    1.29
     Juf
    1.28
     lidl
    1.25
     giovanni
    1.25
    Activations Density 0.305%

    No Known Activations