Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15195
    Prev
    Next
    INDEX
    Explanations

    words related to sound and technology

    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
    +0.18
    1.1%
    67
    +0.12
    0.7%
    1671
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    376
    +0.18
    0.04
    47
    +0.12
    0.04
    67
    +0.11
    0.04
    Negative Logits
    <bos>
    -3.61
    int
    -0.84
    DataContract
    -0.84
    .
    -0.83
    ,
    -0.83
    ⓧ
    -0.81
     int
    -0.80
     engage
    -0.80
    /*---
    -0.78
    hat
    -0.78
    POSITIVE LOGITS
     ftu
    2.37
     fta
    2.36
     affor
    2.36
     bandung
    2.36
     unlaw
    2.35
     maneu
    2.34
     thut
    2.34
     increa
    2.33
     impra
    2.31
     reluct
    2.30
    Activations Density 0.096%

    No Known Activations