© 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. 31305
    Prev
    Next
    INDEX
    Explanations

    references to personal or familial struggles

    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
    340
    +0.13
    0.7%
    441
    +0.12
    0.7%
    212
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.13
    0.07
    212
    +0.12
    0.12
    441
    +0.11
    -0.03
    Negative Logits
    ĥ
    -2.12
    ↵
    -2.06
    ↵↵
    -2.06
     ↵
    -2.06
    ↵
    -2.06
    <|outofrange|>
    -2.06
    <|outofrange|>
    -2.06
    -2.06
    ↵
    -2.06
    -2.06
    POSITIVE LOGITS
     privileges
    1.58
    noreply
    1.52
    }}}$,
    1.52
    }})$,
    1.46
    unnumbered
    1.42
    )}$,
    1.42
    }}^{(
    1.42
     NOTICE
    1.40
    }}}$.
    1.39
     ...)
    1.33
    Activations Density 6.140%

    No Known Activations