© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 551
    Prev
    Next
    INDEX
    Explanations

    phrases related to ethics and obligations, particularly in the context of healthcare

    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
    1399
    +0.08
    0.2%
    1491
    +0.08
    0.2%
    1459
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1399
    +0.08
    0.03
    1459
    +0.08
    0.02
    1136
    +0.08
    0.02
    Negative Logits
     EVANS
    -0.67
     EDWARDS
    -0.60
     PHILLIPS
    -0.58
    ⓧ
    -0.55
    xiu
    -0.55
    NameList
    -0.55
    NoOf
    -0.53
     continúan
    -0.53
    qiao
    -0.51
     intende
    -0.50
    POSITIVE LOGITS
     shouldn
    2.52
     Shouldn
    2.03
     shouldnt
    1.97
     mustn
    1.62
    Shouldn
    1.52
     needn
    1.37
     Violon
    1.04
     aren
    0.94
     weren
    0.94
     Aren
    0.90
    Activations Density 0.159%

    No Known Activations