INDEX

Explanations

phrases or sentences that contain the word "interesting"

oai_token-act-pair · gpt-3.5-turbo

the word "interesting" and its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arest

-0.77

uter

-0.70

oise

-0.70

otent

-0.69

uts

-0.69

reditation

-0.69

ussy

-0.68

esp

-0.65

ILA

-0.65

avers

-0.64

POSITIVE LOGITS

tid

1.05

 juxtap

0.95

 trivia

0.91

 anecdotes

0.90

 twists

0.86

ioned

0.86

 coincidence

0.84

 insights

0.83

 sidel

0.82

 Flavoring

0.80

Activations Density 0.060%

phrases or sentences that contain the word "interesting"

the word "interesting" and its variations in context

No Comments

No Known Activations