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. 14603
    Prev
    Next
    INDEX
    Explanations

    personal nouns and names

    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
    1482
    +0.15
    0.9%
    341
    +0.15
    0.9%
    1677
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1677
    +0.15
    0.04
    314
    +0.15
    0.04
    1097
    +0.15
    0.06
    Negative Logits
    <bos>
    -2.07
    HasAnnotation
    -0.64
    DotNetBar
    -0.58
    MergeFrom
    -0.58
    sidemargin
    -0.57
    doria
    -0.56
     mergeFrom
    -0.56
    PrivateRoute
    -0.55
     оригіналу
    -0.55
    offsetof
    -0.55
    POSITIVE LOGITS
     jaya
    1.20
     kuli
    1.18
     hina
    1.18
     kase
    1.15
     kasa
    1.11
     kani
    1.09
     saar
    1.08
     saha
    1.08
     jawa
    1.07
     jati
    1.05
    Activations Density 0.539%

    No Known Activations