© 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. 0-MLP-SM
    6. 27699
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual named "Robinson."

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    68
    +0.12
    0.7%
    256
    +0.11
    0.6%
    379
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    379
    +0.12
    0.01
    68
    +0.11
    0.01
    66
    +0.11
    0.01
    Negative Logits
    illed
    -1.61
    urred
    -1.52
     thee
    -1.50
    ASE
    -1.46
     slightest
    -1.40
    uv
    -1.39
     moderate
    -1.38
    ]>
    -1.37
    quired
    -1.37
    Č
    -1.36
    POSITIVE LOGITS
    stown
    1.92
    vill
    1.84
    enstein
    1.73
    ship
    1.69
    plete
    1.61
    force
    1.59
    defense
    1.59
    ian
    1.59
    pora
    1.58
    ist
    1.58
    Activations Density 0.014%

    No Known Activations