© 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. 11-RES-JB
    11. 7040
    Prev
    Next
    INDEX
    Explanations

    concepts related to fact-checking and verification

    oai_token-act-pair · gpt-3.5-turbo

    phrases that discuss the concept of "fact" and its implications in various contexts, often in a critical or analytical manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Receiver
    -0.73
     Passenger
    -0.72
     payroll
    -0.70
     exit
    -0.67
     Seasons
    -0.67
     imports
    -0.67
     receipts
    -0.66
     refunds
    -0.66
     wait
    -0.66
     Hai
    -0.65
    POSITIVE LOGITS
    oriented
    1.70
    driven
    1.62
    laden
    1.56
    based
    1.55
    focused
    1.51
    filled
    1.50
    abiding
    1.48
    packed
    1.48
    conscious
    1.46
    loving
    1.46
    Activations Density 0.069%

    No Known Activations