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. 9119
    Prev
    Next
    INDEX
    Explanations

    instances where legal or formal agreements and terms and conditions are mentioned, particularly with entities

    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
    313
    +0.16
    0.9%
    58
    +0.14
    0.7%
    900
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    58
    +0.16
    0.03
    1363
    +0.14
    0.03
    900
    +0.13
    0.03
    Negative Logits
    <bos>
    -1.76
    copg
    -0.63
     Roskov
    -0.61
    AddWithValue
    -0.58
     Michelle
    -0.54
    Література
    -0.53
    Jereo
    -0.53
    CreateIndex
    -0.53
    tolua
    -0.51
     Shang
    -0.50
    POSITIVE LOGITS
     entity
    1.50
     Entity
    1.47
     Entities
    1.37
     entities
    1.35
    entity
    1.26
    Entity
    1.24
    entities
    1.17
    Entities
    1.09
     ENTITY
    1.09
    ENTITY
    1.02
    Activations Density 0.375%

    No Known Activations