© 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. 18643
    Prev
    Next
    INDEX
    Explanations

    sentences where a specific entity "is" or "is not", followed by additional information

    oai_token-act-pair · gpt-3.5-turbo

    phrases that imply the state of being unclear or uncertain

    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
    """
    -0.72
     IMAGES
    -0.62
    HAHAHAHA
    -0.62
     Ancients
    -0.61
     PLUS
    -0.60
    olon
    -0.60
    opathic
    -0.59
    arian
    -0.57
     snipp
    -0.56
    HAHA
    -0.56
    POSITIVE LOGITS
     unclear
    1.71
     unknown
    1.27
     believed
    1.18
     understood
    1.15
     uncertain
    1.12
     conceivable
    1.04
     doubtful
    1.02
     hoped
    1.02
     alleged
    0.96
     customary
    0.96
    Activations Density 0.110%

    No Known Activations