© 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. 26389
    Prev
    Next
    INDEX
    Explanations

    terms related to future predictions or planned events

    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
    23
    +0.17
    0.9%
    282
    +0.12
    0.7%
    292
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    282
    +0.17
    0.09
    327
    +0.12
    0.11
    335
    +0.11
    0.11
    Negative Logits
    ¥
    -3.52
    ¨
    -3.46
    ļ
    -3.33
    IJ
    -3.31
    «
    -3.26
    ®
    -3.22
    µ
    -3.21
    ·
    -3.18
    ¢
    -3.17
    ¤
    -3.13
    POSITIVE LOGITS
    ]>
    1.77
    askell
    1.55
    }\|
    1.49
    ----
    1.45
     Hash
    1.44
    }
    1.42
     thy
    1.41
    ]=
    1.41
     yours
    1.41
    })+
    1.40
    Activations Density 2.252%

    No Known Activations