INDEX

Explanations

expressions of opinions or recommendations

oai_token-act-pair · gpt-3.5-turbo

the word "should" in various contexts related to opinions and recommendations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Puzzle

-0.69

ZI

-0.66

Fra

-0.62

atile

-0.62

ifi

-0.62

fog

-0.61

 Chains

-0.61

 Hits

-0.59

locked

-0.59

cule

-0.58

POSITIVE LOGITS

ered

1.04

be

0.98

ering

0.84

 rightfully

0.83

DragonMagazine

0.81

 beware

0.80

bes

0.80

 ideally

0.79

ublic

0.78

nt

0.78

Activations Density 0.065%

expressions of opinions or recommendations

the word "should" in various contexts related to opinions and recommendations

No Comments

No Known Activations