© 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. Residuals
    9. 2-RES-SM
    11. 28816
    Prev
    Next
    INDEX
    Explanations

    elements related to technical specifications or programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-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_resid_post
    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
    161
    +0.14
    0.8%
    153
    +0.14
    0.8%
    6
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.14
    0.08
    161
    +0.14
    0.04
    6
    +0.13
    0.11
    Negative Logits
    TRODUCTION
    -1.52
    umab
    -1.46
    idenote
    -1.44
     apologies
    -1.41
    gradle
    -1.40
    ]--
    -1.39
    //----------------------------------------------------------------
    -1.37
    kerchief
    -1.36
     (@
    -1.35
    ****************************************************************************
    -1.35
    POSITIVE LOGITS
    »¿
    4.01
    ¾
    3.77
    ¶
    3.72
    ĥ½
    3.63
    º
    3.60
    ľĵ
    3.49
    Ĥ¬
    3.42
    Īĺ
    3.41
    ħ
    3.33
    ĥ
    3.31
    Activations Density 4.801%

    No Known Activations