INDEX

Explanations

keywords or phrases related to prizes

oai_token-act-pair · gpt-3.5-turbo

references to awards or prizes

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

66666666

-0.72

 Ange

-0.72

 Sakuya

-0.71

aturdays

-0.70

icago

-0.70

nian

-0.66

ths

-0.66

oÄŁ

-0.64

ahime

-0.63

 Extrem

-0.62

POSITIVE LOGITS

 prizes

1.14

 prize

1.10

 awarded

1.10

 winners

0.94

 awards

0.93

 winner

0.90

spo

0.86

 Winner

0.86

 Winners

0.86

 laureate

0.85

Activations Density 0.013%

keywords or phrases related to prizes

references to awards or prizes

No Comments

No Known Activations