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. 880
    Prev
    Next
    INDEX
    Explanations

    hyperlink text that instructs the user to interact with it (e.g., "Click", "Click here") in order to access specific content

    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
    1.2%
    1671
    +0.13
    0.8%
    1127
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1671
    +0.20
    0.06
    276
    +0.13
    0.04
    1758
    +0.08
    0.04
    Negative Logits
    <bos>
    -3.10
    CreateIndex
    -0.75
    /*
    -0.74
    <tfoot>
    -0.73
    RepeatedField
    -0.72
    ⓧ
    -0.72
    })();
    
    -0.71
     maintain
    -0.71
     agrí
    -0.69
    public
    -0.69
    POSITIVE LOGITS
     affor
    2.17
     increa
    2.06
     reluct
    2.02
     Juf
    1.97
     maneu
    1.97
     impra
    1.93
     stockholm
    1.91
     accla
    1.89
     impractica
    1.89
     bandung
    1.88
    Activations Density 0.090%

    No Known Activations