© 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. 4-RES-SM
    11. 9095
    Prev
    Next
    INDEX
    Explanations

    specific patterns or repetitions of letters and syllables

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    306
    +0.20
    1.1%
    21
    +0.17
    1.0%
    156
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    134
    +0.20
    0.08
    410
    +0.17
    0.06
    5
    +0.17
    0.02
    Negative Logits
    how
    -1.63
    ]));
    -1.59
    }))
    -1.58
    })}{
    -1.55
    ureus
    -1.54
    lessly
    -1.46
    bucks
    -1.44
    }})$,
    -1.40
    })}\
    -1.40
     })
    -1.40
    POSITIVE LOGITS
    ³
    2.38
    §
    2.20
    ¾
    2.19
    ´
    2.13
    ¢
    2.02
    Ħ
    2.01
    ĵ
    2.01
    ĸ
    2.01
    į
    2.00
    ¡
    1.98
    Activations Density 1.136%

    No Known Activations