INDEX

Explanations

phrases related to negative or alarming situations or predictions

oai_token-act-pair · gpt-3.5-turbo

the word "the" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

thood

-0.73

imi

-0.70

Ò

-0.69

leeve

-0.69

athon

-0.69

cheon

-0.68

leground

-0.66

!!

-0.65

!!!!

-0.65

CHAPTER

-0.65

POSITIVE LOGITS

 slightest

1.45

 entire

1.28

 remainder

1.23

 latter

1.14

 whole

1.14

 majority

1.11

 resultant

1.10

 entirety

1.09

 resulting

1.07

 result

1.06

Activations Density 0.495%

phrases related to negative or alarming situations or predictions

the word "the" in various contexts

No Comments

No Known Activations