INDEX

Explanations

mentions of awards or winning

oai_token-act-pair · gpt-3.5-turbo

references to various awards and accolades

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

ths

-0.76

 Archangel

-0.64

ohyd

-0.63

 Breat

-0.63

 Sins

-0.62

 Occupations

-0.61

 Rebell

-0.60

 Leilan

-0.60

 impe

-0.59

 Anon

-0.59

POSITIVE LOGITS

 awards

1.10

 awarded

1.01

 laure

0.99

 nominations

0.97

 prizes

0.94

Winner

0.94

 winner

0.93

 awarding

0.90

 award

0.89

 winners

0.87

Activations Density 0.021%

mentions of awards or winning

references to various awards and accolades

No Comments

No Known Activations