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

    Neuronpedia

    Jacobian LensNEW
    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. 0-MLP-SM
    11. 29310
    Prev
    Next
    INDEX
    Explanations

    legal citations or references within the text

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    224
    +0.12
    0.7%
    494
    +0.11
    0.6%
    76
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.12
    0.02
    24
    +0.11
    0.02
    494
    +0.11
    0.02
    Negative Logits
    ophil
    -1.53
     conduct
    -1.48
     ORDERED
    -1.46
    respectively
    -1.44
    ject
    -1.42
    asting
    -1.42
    ars
    -1.40
    aster
    -1.40
    osevelt
    -1.39
     ](
    -1.38
    POSITIVE LOGITS
    nier
    1.83
    naire
    1.68
    ioned
    1.59
    ync
    1.58
    fully
    1.57
    née
    1.56
    iously
    1.56
    vous
    1.53
    led
    1.53
     outfits
    1.51
    Activations Density 3.887%

    No Known Activations