INDEX

Explanations

phrases related to spatial locations or directions

oai_token-act-pair · gpt-3.5-turbo

repeated uses of 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

thood

-0.81

cially

-0.79

HCR

-0.73

bourg

-0.69

ItemThumbnailImage

-0.68

videos

-0.67

manship

-0.67

Gene

-0.66

olicy

-0.66

otech

-0.65

POSITIVE LOGITS

 vicinity

1.10

 doorway

1.03

 bushes

1.03

 ceiling

1.02

 pavement

1.02

 nearest

1.01

 midst

1.01

 depths

0.99

 periphery

0.98

 outskirts

0.98

Activations Density 0.343%

phrases related to spatial locations or directions

repeated uses of the word "the" in various contexts

No Comments

No Known Activations