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. 929
    Prev
    Next
    INDEX
    Explanations

    terms related to the Social Security Death Index and its processes

    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
    521
    +0.15
    0.6%
    1438
    +0.13
    0.5%
    559
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.15
    0.05
    1622
    +0.13
    0.04
    1896
    +0.13
    0.04
    Negative Logits
    <bos>
    -1.18
     مرئيه
    -0.99
    MessageOf
    -0.75
    ValueStyle
    -0.75
     Waray
    -0.74
     insuffisamment
    -0.65
     AssemblyCulture
    -0.62
     Roskov
    -0.62
    estream
    -0.61
    Tē
    -0.61
    POSITIVE LOGITS
     impra
    1.30
     reluct
    1.18
     suscep
    1.17
     unwarran
    1.17
     increa
    1.15
     ineffec
    1.14
     friable
    1.11
     unlaw
    1.10
     disagre
    1.09
     apprehen
    1.07
    Activations Density 0.487%

    No Known Activations