INDEX

Explanations

phrases containing the words "could not"

oai_token-act-pair · gpt-3.5-turbo

negations, specifically variations of the phrase "could not."

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

interstitial

-0.73

soDeliveryDate

-0.72

quickShipAvailable

-0.69

 Appears

-0.68

cloth

-0.66

cases

-0.63

 Signs

-0.61

 Called

-0.61

 Mant

-0.61

plates

-0.61

POSITIVE LOGITS

 afford

1.06

 foresee

0.99

 adequately

0.85

 tolerate

0.82

icably

0.82

 cope

0.80

 necessarily

0.80

 feas

0.80

 distinguish

0.80

 convince

0.79

Activations Density 0.051%

phrases containing the words "could not"

negations, specifically variations of the phrase "could not."

No Comments

No Known Activations