INDEX

Explanations

comparisons of quantity or degree, particularly emphasizing one thing as being more or less than another

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize the concept of "more."

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

lees

-0.89

 Travels

-0.84

 Committees

-0.74

æ©

-0.73

 Releases

-0.72

seconds

-0.70

marks

-0.69

bows

-0.69

 Dancing

-0.69

ONES

-0.68

POSITIVE LOGITS

 complicated

1.06

 efficient

1.05

 expansive

0.99

 elaborate

0.99

 detailed

0.99

 manageable

0.97

 nuanced

0.96

 plausible

0.96

 convenient

0.92

than

0.92

Activations Density 0.066%

comparisons of quantity or degree, particularly emphasizing one thing as being more or less than another

phrases that emphasize the concept of "more."

No Comments

No Known Activations