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. 6825
    Prev
    Next
    INDEX
    Explanations

    book titles and publishers

    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
    0.6%
    1343
    +0.11
    0.4%
    1150
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    924
    +0.17
    0.04
    1343
    +0.11
    0.04
    771
    +0.09
    0.03
    Negative Logits
    <bos>
    -2.03
    RegressionTest
    -0.99
    MessageOf
    -0.95
    wikidata
    -0.94
    IsContent
    -0.92
    UnusedPrivate
    -0.88
    BufferException
    -0.86
    ByVersion
    -0.86
    RotationOrder
    -0.85
    MarshalTo
    -0.84
    POSITIVE LOGITS
     maneu
    1.48
     affor
    1.48
     reluct
    1.41
     hairc
    1.41
     madonna
    1.39
     milf
    1.38
     snoopy
    1.37
     wherea
    1.35
     cushi
    1.32
     Juf
    1.31
    Activations Density 0.111%

    No Known Activations