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. 560
    Prev
    Next
    INDEX
    Explanations

    links, addresses, or specific details within a text

    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
    +0.17
    0.7%
    1413
    +0.10
    0.4%
    506
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1413
    +0.17
    0.05
    559
    +0.10
    0.05
    82
    +0.08
    0.04
    Negative Logits
    <bos>
    -2.55
    SequentialGroup
    -0.69
    ⓧ
    -0.65
    principalColumn
    -0.63
    +#+
    -0.62
     Waray
    -0.59
    intios
    -0.59
    forChild
    -0.56
     sexu
    -0.56
    ുറ
    -0.56
    POSITIVE LOGITS
     reluct
    1.10
     accla
    1.08
     maneu
    1.08
     philanth
    1.05
     milf
    1.00
     affor
    0.98
     fortn
    0.96
     shenan
    0.95
     disreg
    0.95
     erad
    0.94
    Activations Density 0.311%

    No Known Activations