INDEX

Explanations

references to prizes or rewards

oai_token-act-pair · gpt-3.5-turbo

references to monetary prizes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Sakuya

-0.80

 Ange

-0.76

icago

-0.74

ahime

-0.71

66666666

-0.70

pher

-0.68

ford

-0.66

ansion

-0.66

aturdays

-0.65

POSITIVE LOGITS

 prizes

1.12

 prize

1.09

 awarded

1.08

 awards

0.96

 winners

0.93

 purse

0.90

 winner

0.90

 award

0.88

 laureate

0.88

 Winner

0.85

Activations Density 0.020%

references to prizes or rewards

references to monetary prizes

No Comments

No Known Activations