INDEX

Explanations

phrases related to uncertainty and confirmation

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate the state or condition of something

oai_token-act-pair · gpt-4o-mini Triggered 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

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pmwiki

-0.99

Parameters

-0.80

SPONSORED

-0.78

ieties

-0.74

Marginal

-0.72

 lengths

-0.71

*/(

-0.69

itÃ©

-0.69

è¦ļéĨĴ

-0.68

estyles

-0.68

POSITIVE LOGITS

 genuine

1.16

 legit

1.14

 authentic

1.13

 real

1.10

 indeed

1.08

 true

1.05

 theirs

1.01

 actually

1.00

 fake

0.97

 hers

0.96

Activations Density 0.276%

phrases related to uncertainty and confirmation

phrases that indicate the state or condition of something

No Comments

No Known Activations