© 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. 10-RES-JB
    11. 20257
    Prev
    Next
    INDEX
    Explanations

    terms related to verifying information and processing orders

    oai_token-act-pair · gpt-3.5-turbo

    references to dates and associated context in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rivals
    -0.75
    uries
    -0.74
     billions
    -0.71
    fights
    -0.69
    humans
    -0.65
    attacks
    -0.65
     ponds
    -0.64
     roofs
    -0.64
     raids
    -0.63
     lately
    -0.63
    POSITIVE LOGITS
     invoice
    1.15
     receipt
    1.05
    idav
    1.04
     mailed
    0.99
     photoc
    0.98
     emailed
    0.98
    fax
    0.97
     confirmation
    0.95
     confirming
    0.94
     receipts
    0.94
    Activations Density 0.355%

    No Known Activations