INDEX

Explanations

phrases that express agreement or confirmation

oai_token-act-pair · gpt-3.5-turbo

affirmative responses and expressions of agreement

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 embroiled

-0.72

ounded

-0.65

agna

-0.65

oodle

-0.62

enta

-0.61

ciplinary

-0.61

Tec

-0.60

 backfield

-0.58

anticipated

-0.55

ouls

-0.55

POSITIVE LOGITS

 yeah

1.06

yeah

0.97

sir

0.91

 Exactly

0.90

Yeah

0.87

 Absolutely

0.83

 Yeah

0.79

soType

0.75

yes

0.73

uh

0.73

Activations Density 0.106%

phrases that express agreement or confirmation

affirmative responses and expressions of agreement

No Comments

No Known Activations