INDEX

Explanations

phrases related to exceeding or over-extending limits or boundaries

oai_token-act-pair · gpt-3.5-turbo

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

Brave

-0.71

iframe

-0.71

minster

-0.67

ioxide

-0.66

PLA

-0.64

behind

-0.63

ichael

-0.62

wick

-0.59

spot

-0.58

letters

-0.58

POSITIVE LOGITS

xual

0.93

ealous

0.84

adows

0.77

ukong

0.71

 caution

0.71

whel

0.69

 hype

0.67

whelming

0.66

agog

0.65

dden

0.64

Activations Density 0.123%

phrases related to exceeding or over-extending limits or boundaries

No Comments

No Known Activations