INDEX

Explanations

mentions of credits or acknowledgments in the text

oai_token-act-pair · gpt-3.5-turbo

mentions of "credit" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pacif

-0.81

vae

-0.67

ittle

-0.67

 communist

-0.64

 ashore

-0.64

 grun

-0.63

 silent

-0.60

enium

-0.59

 marsh

-0.59

fog

-0.58

POSITIVE LOGITS

Credit

1.63

 Credit

1.09

credit

1.04

Credits

0.97

 Credits

0.96

 Shutterstock

0.88

displayText

0.87

Screenshot

0.85

 Caption

0.85

tesy

0.84

Activations Density 0.004%

mentions of credits or acknowledgments in the text

mentions of "credit" in various contexts

No Comments

No Known Activations