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. 4459
    Prev
    Next
    INDEX
    Explanations

    references to movie sequels

    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
    +0.25
    0.9%
    776
    +0.10
    0.4%
    1173
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.25
    0.08
    1529
    +0.10
    0.06
    1762
    +0.09
    0.05
    Negative Logits
    <bos>
    -2.70
     Administrativna
    -0.75
    ⓧ
    -0.73
    Autoritní
    -0.70
    ConstraintMaker
    -0.70
    ynb
    -0.66
    public
    -0.65
     <=",
    -0.65
    declare
    -0.64
    clable
    -0.64
    POSITIVE LOGITS
     affor
    2.22
     impra
    2.10
     maneu
    2.09
     disagre
    2.09
     increa
    1.99
     accla
    1.99
     reluct
    1.97
     sophistic
    1.93
     shenan
    1.91
     unspeak
    1.90
    Activations Density 0.772%

    No Known Activations