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. 5364
    Prev
    Next
    INDEX
    Explanations

    the character 'm'

    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
    +0.18
    1.1%
    896
    +0.12
    0.7%
    411
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    577
    +0.18
    0.03
    1256
    +0.12
    0.03
    1705
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.77
     springfox
    -0.74
    
    
    -0.71
    ⓧ
    -0.68
     cooperated
    -0.67
    <?
    -0.65
     inaugurate
    -0.64
     saluted
    -0.63
     cooperate
    -0.61
     reinstate
    -0.61
    POSITIVE LOGITS
     m
    1.08
     quoique
    0.92
     délib
    0.92
     alté
    0.90
    m
    0.89
     Cfr
    0.87
     bourgeo
    0.85
    mId
    0.85
     citoy
    0.85
     médic
    0.84
    Activations Density 0.116%

    No Known Activations