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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 25371
    Prev
    Next
    INDEX
    Explanations

    mentions of frameworks, standards, or principles related to ethics and social responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_mlp_out
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    111
    +0.14
    0.8%
    429
    +0.14
    0.8%
    169
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    169
    +0.14
    0.13
    437
    +0.14
    0.11
    71
    +0.12
    0.12
    Negative Logits
    }$).
    -1.82
     itself
    -1.69
    !--
    -1.60
    $).
    -1.57
    }}})$
    -1.55
    }$),
    -1.52
    \]).
    -1.50
    "));
    -1.50
    ").
    -1.49
    })$.
    -1.49
    POSITIVE LOGITS
    »¿
    3.25
    3.15
    č↵
    3.15
    <|outofrange|>
    3.15
    ↵
    3.15
    ↵
    3.15
    3.15
    ↵
    3.15
    č↵
    3.15
    3.15
    Activations Density 1.627%

    No Known Activations