© 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 EvalsExportsinterp-engineNEWAPI 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. 27577
    Prev
    Next
    INDEX
    Explanations

    details about services or offerings, especially those associated with events or hospitality

    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
    479
    +0.14
    0.8%
    271
    +0.13
    0.7%
    487
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    391
    +0.14
    0.06
    21
    +0.13
    0.05
    271
    +0.13
    -0.01
    Negative Logits
    .";
    -2.28
    ";
    -2.03
     ();
    -1.90
    ';
    -1.72
    <>();
    -1.65
    ”;
    -1.64
    ?”
    -1.62
    ”.
    -1.60
    .”
    -1.60
     };
    -1.52
    POSITIVE LOGITS
     *)
    1.83
    ))/
    1.72
    ))=
    1.56
    ))^
    1.55
    ]{})
    1.55
    ]),
    1.48
    attle
    1.47
    ).)
    1.44
    ),
    1.43
    ]):
    1.42
    Activations Density 1.122%

    No Known Activations