© 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. 9879
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences with reported speech, particularly with the verb "said"

    oai_token-act-pair · gpt-3.5-turbo

    instances of reported speech

    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
    phia
    -0.70
    arent
    -0.67
     Skydragon
    -0.62
    AMS
    -0.59
    pend
    -0.59
    Pont
    -0.58
    hub
    -0.58
    berus
    -0.58
    ppings
    -0.58
    icial
    -0.55
    POSITIVE LOGITS
     sarcast
    1.18
     bluntly
    1.09
     emphatically
    1.08
     aloud
    1.07
     confidently
    1.06
     calmly
    1.02
     proudly
    1.00
     softly
    0.99
     passionately
    0.99
     rhet
    0.96
    Activations Density 0.106%

    No Known Activations