INDEX

Explanations

dates expressed as the year

oai_token-act-pair · gpt-3.5-turbo

instances of time-related phrases, especially those indicating a specific point in the past

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

¬¼

-0.69

eries

-0.68

tro

-0.67

atio

-0.66

irc

-0.66

alogy

-0.65

 Generic

-0.60

asma

-0.59

natureconservancy

-0.59

roid

-0.59

POSITIVE LOGITS

 according

0.95

 although

0.91

 culminating

0.89

 prompting

0.85

huh

0.82

 marking

0.81

 leaving

0.80

when

0.79

 namely

0.79

 albeit

0.78

Activations Density 0.314%

dates expressed as the year

instances of time-related phrases, especially those indicating a specific point in the past

No Comments

No Known Activations