INDEX

Explanations

phrases indicating future actions or states

oai_token-act-pair · gpt-3.5-turbo

phrases featuring "be" and its various conjugations indicating future actions or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

raq

-0.75

annot

-0.73

Express

-0.69

 Mans

-0.67

 foresee

-0.67

arte

-0.66

 Tale

-0.66

Unt

-0.65

 thereto

-0.65

Therefore

-0.63

POSITIVE LOGITS

nova

0.86

 pandemonium

0.83

ypes

0.74

 trouble

0.73

 alright

0.72

hin

0.72

 messed

0.71

massive

0.71

ezvous

0.70

fuck

0.70

Activations Density 0.138%

phrases indicating future actions or states

phrases featuring "be" and its various conjugations indicating future actions or states

No Comments

No Known Activations