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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26340
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and associated language

    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
    356
    +0.13
    0.7%
    497
    +0.12
    0.6%
    25
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    356
    +0.13
    0.08
    2
    +0.12
    0.07
    91
    +0.11
    0.06
    Negative Logits
    Ĥ
    -2.24
    ī
    -2.21
    ¿½
    -2.14
    ı
    -2.13
    ħ
    -2.13
    ¸
    -2.03
    ĥ
    -1.99
    Ĥ¬
    -1.95
    ª
    -1.93
    »
    -1.93
    POSITIVE LOGITS
    IFIC
    1.49
    FromString
    1.47
     deduct
    1.42
    "}](#
    1.42
    CDATA
    1.42
    ]{}]{}
    1.42
     ({
    1.42
    ]];
    1.41
     datetime
    1.41
    opian
    1.37
    Activations Density 0.476%

    No Known Activations