© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26562
    Prev
    Next
    INDEX
    Explanations

    terms associated with the concept of "effects" in various contexts

    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
    435
    +0.16
    0.9%
    44
    +0.13
    0.7%
    193
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.16
    0.03
    462
    +0.13
    0.02
    78
    +0.12
    0.02
    Negative Logits
    ĻĤ
    -2.15
    Ļª
    -2.06
    ĺ
    -1.94
    ľ
    -1.92
    ħ
    -1.78
    Ħ
    -1.74
     trouble
    -1.70
    ¨
    -1.67
    į
    -1.65
    ersion
    -1.64
    POSITIVE LOGITS
    views
    1.55
     wand
    1.48
    _:
    1.47
    fo
    1.44
    office
    1.43
    ÃŃc
    1.43
    held
    1.42
    ipel
    1.42
    enez
    1.41
     anything
    1.38
    Activations Density 0.097%

    No Known Activations