INDEX

Explanations

phrases related to immediate action or urgency

oai_token-act-pair · gpt-3.5-turbo

phrases indicating immediate action or urgency

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

alg

-0.82

MAC

-0.73

lain

-0.73

gall

-0.72

oft

-0.71

sels

-0.71

adr

-0.71

orously

-0.70

vari

-0.69

orius

-0.68

POSITIVE LOGITS

Introduced

0.76

aneously

0.76

ODY

0.69

erker

0.68

 earthqu

0.60

ETHOD

0.60

 dispatch

0.60

ailability

0.60

 Gomez

0.59

 glance

0.57

Activations Density 0.029%

phrases related to immediate action or urgency

phrases indicating immediate action or urgency

No Comments

No Known Activations