Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 17
    Prev
    Next
    INDEX
    Explanations

    terms related to X-ray technology and vulnerabilities

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    904
    +0.07
    0.2%
    1810
    +0.06
    0.2%
    1232
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.07
    0.03
    1343
    +0.06
    0.06
    1884
    +0.06
    0.04
    Negative Logits
     cu
    -0.91
     an
    -0.83
     must
    -0.83
     I
    -0.83
     bar
    -0.82
     over
    -0.82
     won
    -0.82
     min
    -0.81
     so
    -0.81
     *
    -0.80
    POSITIVE LOGITS
     fta
    3.07
     ftu
    3.01
     increa
    2.89
     thut
    2.83
     squa
    2.81
     aen
    2.78
     fup
    2.76
     ftre
    2.74
     wherea
    2.73
     maneu
    2.69
    Activations Density 0.366%

    No Known Activations