INDEX

Explanations

prepositional phrases indicating the location of something

oai_token-act-pair · gpt-3.5-turbo

prepositions and specific phrases that indicate context or location

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

ornings

-0.83

Ļ½

-0.75

ĺħ

-0.74

ģĸ

-0.72

haps

-0.69

unte

-0.69

WD

-0.67

aspers

-0.65

©¶æ¥µ

-0.65

ĨĴ

-0.64

POSITIVE LOGITS

liest

1.07

iest

0.78

 itself

0.73

 question

0.71

hest

0.67

 portion

0.66

elight

0.64

 whence

0.64

 Huntington

0.64

osphere

0.63

Activations Density 1.508%

prepositional phrases indicating the location of something

prepositions and specific phrases that indicate context or location

No Comments

No Known Activations