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. 5691
    Prev
    Next
    INDEX
    Explanations

    phrases related to permissions and restrictions

    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
    +0.20
    0.8%
    2036
    +0.10
    0.4%
    172
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    707
    +0.20
    0.05
    2036
    +0.10
    0.04
    1314
    +0.08
    0.04
    Negative Logits
    <bos>
    -2.67
     initComponents
    -0.84
    ///</
    -0.84
    AutoScaleMode
    -0.82
    devServer
    -0.79
     ModelExpression
    -0.79
    CreateIndex
    -0.79
    })();
    
    -0.78
    mergeFrom
    -0.77
    SharedCtor
    -0.76
    POSITIVE LOGITS
     maneu
    2.46
     affor
    2.19
     reluct
    2.11
     depic
    2.08
     increa
    2.08
     impra
    2.07
     Confu
    2.03
     strick
    2.02
     volunte
    2.00
     indestru
    2.00
    Activations Density 0.428%

    No Known Activations