INDEX

Explanations

phrases starting with "Perhaps."

oai_token-act-pair · gpt-3.5-turbo

the word "perhaps" and its variations, indicating uncertainty or speculation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ocaust

-0.83

ËĪ

-0.74

foreseen

-0.72

SPONSORED

-0.70

natureconservancy

-0.69

clock

-0.68

documented

-0.68

ãĤĬ

-0.66

``

-0.65

RAW

-0.64

POSITIVE LOGITS

 someday

1.06

 unsurprisingly

0.80

 someone

0.76

 somebody

0.76

we

0.73

 Tomorrow

0.72

 there

0.72

 they

0.71

 sensing

0.70

 thats

0.68

Activations Density 0.085%

phrases starting with "Perhaps."

the word "perhaps" and its variations, indicating uncertainty or speculation

No Comments

No Known Activations