INDEX

Explanations

phrases suggesting uncertainty or possibility, typically starting with the word "Perhaps" or "Maybe"

oai_token-act-pair · gpt-3.5-turbo

expressions of 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 @ 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

seller

-0.78

zeb

-0.77

natureconservancy

-0.76

ife

-0.75

own

-0.74

ocaust

-0.73

arial

-0.73

efer

-0.72

version

-0.72

irements

-0.71

POSITIVE LOGITS

 someday

0.81

 unsurprisingly

0.75

 sensing

0.74

 tempted

0.70

 consolation

0.68

 impeachment

0.67

 Tomorrow

0.67

 suppose

0.66

 Nost

0.65

 fate

0.65

Activations Density 0.047%

phrases suggesting uncertainty or possibility, typically starting with the word "Perhaps" or "Maybe"

expressions of uncertainty or speculation

No Comments

No Known Activations