INDEX

Explanations

proper nouns or phrases related to historical events or entities

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Great" 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 @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

SPONSORED

-0.78

ople

-0.76

ktop

-0.72

isSpecialOrderable

-0.71

NetMessage

-0.71

tle

-0.70

ev

-0.69

weights

-0.68

rez

-0.66

mun

-0.65

POSITIVE LOGITS

 Great

1.05

Great

0.84

 Recession

0.81

great

0.78

 Divide

0.75

sword

0.74

 Warranty

0.74

 Lakes

0.73

 Barrier

0.73

 Idea

0.70

Activations Density 0.018%

proper nouns or phrases related to historical events or entities

occurrences of the word "Great" in various contexts

No Comments

No Known Activations