INDEX

Explanations

expressions related to expressing satisfaction or dissatisfaction

oai_token-act-pair · gpt-3.5-turbo

expressions of dissatisfaction or negative emotions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

verend

-0.66

arest

-0.65

selves

-0.65

brance

-0.65

 continuum

-0.63

uilding

-0.63

ilial

-0.62

bis

-0.61

inguishable

-0.60

miah

-0.60

POSITIVE LOGITS

 himself

1.23

 herself

0.95

his

0.89

 Himself

0.76

 tweeting

0.75

 yesterday

0.75

 commenting

0.74

 Tuesday

0.70

 amused

0.68

 Wednesday

0.68

Activations Density 0.674%

expressions related to expressing satisfaction or dissatisfaction

expressions of dissatisfaction or negative emotions

No Comments

No Known Activations