INDEX

Explanations

phrases indicating uncertainty or speculation

oai_token-act-pair · gpt-3.5-turbo

phrases indicating hypothetical scenarios or speculation

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

srf

-0.65

edom

-0.65

otypes

-0.65

train

-0.65

arius

-0.65

viks

-0.65

aries

-0.64

loads

-0.63

spe

-0.63

ps

-0.63

POSITIVE LOGITS

lihood

0.72

ILLE

0.65

 admitting

0.64

 causation

0.64

oche

0.64

lication

0.62

wcsstore

0.61

 dismissing

0.60

 they

0.60

 unemploy

0.59

Activations Density 0.011%

phrases indicating uncertainty or speculation

phrases indicating hypothetical scenarios or speculation

No Comments

No Known Activations