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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 765
    Prev
    Next
    INDEX
    Explanations

    names of individuals

    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
    1994
    +0.11
    0.5%
    201
    +0.11
    0.5%
    1575
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.11
    0.10
    2044
    +0.11
    0.07
    1575
    +0.10
    0.06
    Negative Logits
     Hieronymus
    -0.71
     Annika
    -0.67
     Karsten
    -0.64
     Katja
    -0.63
     Shakspeare
    -0.63
    Jörg
    -0.62
     Jörg
    -0.61
     pageIndex
    -0.61
     michelle
    -0.61
     Giovanna
    -0.61
    POSITIVE LOGITS
     kac
    1.05
     Portail
    0.95
     panik
    0.94
     karton
    0.93
     kram
    0.90
     makro
    0.88
     Dés
    0.88
     seksi
    0.88
     usta
    0.85
     Chá
    0.85
    Activations Density 0.323%

    No Known Activations