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. 5587
    Prev
    Next
    INDEX
    Explanations

    advice and instructions, emphasizing prayer and community involvement

    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
    +0.15
    0.5%
    872
    +0.08
    0.3%
    1120
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.15
    0.04
    1703
    +0.08
    0.04
    1659
    +0.07
    0.04
    Negative Logits
    <bos>
    -2.09
    toHaveBeen
    -0.69
    CppMethod
    -0.66
     disambiguazione
    -0.65
     defaultstate
    -0.63
     nahilalakip
    -0.63
     Walkover
    -0.61
    addComponent
    -0.61
    Kontrola
    -0.61
    AutoScaleMode
    -0.60
    POSITIVE LOGITS
     philanth
    1.92
     volunte
    1.71
     pamph
    1.67
     shenan
    1.66
     accla
    1.60
     practition
    1.58
     affor
    1.56
     reluct
    1.51
     unlaw
    1.50
     coö
    1.49
    Activations Density 0.194%

    No Known Activations