INDEX

Explanations

the word "buff" or variations of it

oai_token-act-pair · gpt-3.5-turbo

references to the word "buff" 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

________________________

-0.75

 Labyrinth

-0.65

 Stras

-0.65

PF

-0.63

ELE

-0.63

 VIDEOS

-0.61

FTWARE

-0.61

QUIRE

-0.60

 Reign

-0.59

 Dresden

-0.58

POSITIVE LOGITS

alon

1.10

alos

1.10

ered

1.07

alo

0.99

ington

0.96

ering

0.96

aign

0.93

oon

0.93

ett

0.92

aroo

0.88

Activations Density 0.006%

the word "buff" or variations of it

references to the word "buff" in various contexts

No Comments

No Known Activations