INDEX

Explanations

phrases related to quick explanations or descriptions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "brief."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ceans

-0.79

âĹ¼

-0.78

JV

-0.76

GO

-0.67

GREEN

-0.65

rogens

-0.65

DO

-0.65

IVER

-0.64

ç¥ŀ

-0.63

 Polo

-0.63

POSITIVE LOGITS

cases

1.22

case

1.15

 stint

0.88

erate

0.86

 glimps

0.85

aneously

0.84

ebin

0.80

itud

0.78

 outline

0.76

ftime

0.75

Activations Density 0.016%

phrases related to quick explanations or descriptions

occurrences of the word "brief."

No Comments

No Known Activations