INDEX

Explanations

phrases indicating the conclusion or end of a statement or discussion

oai_token-act-pair · gpt-3.5-turbo

terms related to conclusions or definitively stated outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

href

-0.81

activated

-0.76

otin

-0.72

drivers

-0.72

ez

-0.69

cler

-0.68

ithing

-0.68

dos

-0.67

enta

-0.66

map

-0.66

POSITIVE LOGITS

 concluding

0.92

 concludes

0.91

 conclude

0.88

 conclusion

0.82

 concluded

0.81

uations

0.75

reement

0.75

itute

0.73

iary

0.71

 FANTASY

0.71

Activations Density 0.011%

phrases indicating the conclusion or end of a statement or discussion

terms related to conclusions or definitively stated outcomes

No Comments

No Known Activations