INDEX

Explanations

expressions of gratitude or thanks

oai_token-act-pair · gpt-3.5-turbo

phrases that express a desire or preference

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

VERTISEMENT

-0.80

angular

-0.71

ingen

-0.69

icol

-0.69

ulty

-0.66

onut

-0.65

aan

-0.62

shock

-0.62

@#&

-0.61

illusion

-0.61

POSITIVE LOGITS

lier

0.82

 revenge

0.75

 assurances

0.69

to

0.67

lihood

0.66

 forgiveness

0.65

fully

0.63

ANY

0.61

 redress

0.61

ably

0.61

Activations Density 0.024%

expressions of gratitude or thanks

phrases that express a desire or preference

No Comments

No Known Activations