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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 193
    Prev
    Next
    INDEX
    Explanations

    technical information related to forums or mailing lists

    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
    1023
    +0.14
    0.6%
    1376
    +0.14
    0.6%
    1520
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.14
    0.03
    1343
    +0.14
    0.04
    478
    +0.14
    0.01
    Negative Logits
    Mhm
    -0.65
    enterOuterAlt
    -0.62
     préférable
    -0.59
    <bos>
    -0.56
     évident
    -0.56
     kubwa
    -0.55
     nzuri
    -0.55
     bawat
    -0.53
    Obrázky
    -0.53
     Rech
    -0.53
    POSITIVE LOGITS
     autunno
    1.12
     --------------
    0.96
     particolar
    0.91
     tramont
    0.89
     marcato
    0.85
     paradiso
    0.85
     incess
    0.85
     divertimento
    0.85
     tranquillo
    0.84
     quegli
    0.83
    Activations Density 0.289%

    No Known Activations