INDEX

Explanations

questions at the end of sentences

oai_token-act-pair · gpt-3.5-turbo

questions or inquiries, particularly those seeking clarification or understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

athe

-0.76

ema

-0.72

 evening

-0.72

 background

-0.70

cipled

-0.66

aku

-0.66

 swamp

-0.66

yak

-0.66

 flagged

-0.66

 guiActiveUnfocused

-0.65

POSITIVE LOGITS

 Well

1.22

 Turns

1.05

 Probably

1.05

 Surely

1.05

 Aren

1.04

 Firstly

1.02

 Perhaps

1.02

Why

1.00

 Answer

0.99

 Certainly

0.98

Activations Density 0.093%

questions at the end of sentences

questions or inquiries, particularly those seeking clarification or understanding

No Comments

No Known Activations