© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 4043
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of reconciliation

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to reconciliation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ail
    -0.70
    worm
    -0.67
     Domain
    -0.62
     Insect
    -0.62
    Beta
    -0.62
    Die
    -0.61
     spikes
    -0.61
    rb
    -0.60
    onte
    -0.60
    Fi
    -0.60
    POSITIVE LOGITS
     reconciliation
    4.10
     reconc
    2.63
     reconcil
    2.55
     reconcile
    2.24
     Recon
    2.07
     reun
    1.60
     unification
    1.36
     reunion
    1.32
     mediation
    1.31
    iliation
    1.24
    Activations Density 0.019%

    No Known Activations