INDEX

Explanations

numerical values related to an increase or decrease

oai_token-act-pair · gpt-3.5-turbo

phrases indicating changes in numerical values or statistics, particularly increases and decreases

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

ty

-0.76

mop

-0.72

eur

-0.72

Anth

-0.64

WI

-0.62

gee

-0.62

pas

-0.60

 Founding

-0.60

>[

-0.59

æµ

-0.58

POSITIVE LOGITS

graded

1.10

grading

1.00

 sharply

0.93

grades

0.84

aez

0.84

vertisement

0.79

 compr

0.78

 marginally

0.76

baugh

0.75

xual

0.74

Activations Density 0.044%

numerical values related to an increase or decrease

phrases indicating changes in numerical values or statistics, particularly increases and decreases

No Comments

No Known Activations