INDEX

Explanations

references to weather conditions, especially focusing on temperatures

oai_token-act-pair · gpt-3.5-turbo

phrases related to temperature and weather conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Transaction

-0.75

senal

-0.74

 Unch

-0.72

upe

-0.71

Repl

-0.70

CHA

-0.69

Translation

-0.66

umbn

-0.65

NXT

-0.65

 Decoder

-0.64

POSITIVE LOGITS

 temperatures

1.52

 weather

1.36

 winters

1.33

 rains

1.27

 rainy

1.25

 winds

1.23

 humidity

1.23

 conditions

1.20

 climates

1.18

 summers

1.17

Activations Density 0.219%

references to weather conditions, especially focusing on temperatures

phrases related to temperature and weather conditions

No Comments

No Known Activations