© 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. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 26456
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to electronics and circuit design

    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
    114
    +0.12
    0.7%
    431
    +0.12
    0.7%
    337
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    164
    +0.12
    0.05
    38
    +0.12
    -0.01
    141
    +0.12
    0.06
    Negative Logits
    ]{}]{}
    -1.96
     applause
    -1.57
     objection
    -1.49
     herein
    -1.47
    iorari
    -1.46
    .]{}
    -1.42
     thereto
    -1.42
    hibition
    -1.42
    à°¿
    -1.40
    \]](
    -1.39
    POSITIVE LOGITS
    Ļª
    2.10
    Īĺ
    1.83
    İ
    1.66
    adian
    1.47
    %;
    1.44
    Ĺ
    1.44
    adin
    1.44
    __(
    1.42
    °
    1.42
    ®
    1.40
    Activations Density 1.275%

    No Known Activations