© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 7814
    Prev
    Next
    INDEX
    Explanations

    phrases containing slang terms like "dude" and casual conversation expressions

    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
    220
    +0.12
    0.5%
    1335
    +0.12
    0.5%
    204
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    220
    +0.12
    0.04
    1363
    +0.12
    0.03
    1335
    +0.11
    0.04
    Negative Logits
    <bos>
    -1.82
    /***
    -0.79
    Bibliograf
    -0.72
    lateinit
    -0.70
    RTLR
    -0.67
    IonicModule
    -0.66
    AutoScaleMode
    -0.61
    Identyfik
    -0.60
     makro
    -0.59
    revalidate
    -0.58
    POSITIVE LOGITS
     ecru
    1.28
     swarovski
    1.25
     unlaw
    1.24
     Shakspeare
    1.23
     felicity
    1.21
     liberality
    1.20
     unwarran
    1.13
     withal
    1.11
     impractica
    1.08
     riviera
    1.07
    Activations Density 0.342%

    No Known Activations