INDEX

Explanations

prepositions followed by nouns, especially those indicating possession or relationship between entities

oai_token-act-pair · gpt-3.5-turbo

prepositional phrases indicating relationships or comparisons

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

CAST

-0.68

alities

-0.64

ities

-0.62

igans

-0.61

anon

-0.60

ART

-0.60

adesh

-0.59

 VIDEOS

-0.59

ITIES

-0.59

ats

-0.59

POSITIVE LOGITS

 meanwhile

0.84

ccording

0.78

cussion

0.74

jri

0.69

 meantime

0.67

 sensing

0.65

 hereby

0.64

 however

0.64

 furthermore

0.62

 moder

0.62

Activations Density 0.161%

prepositions followed by nouns, especially those indicating possession or relationship between entities

prepositional phrases indicating relationships or comparisons

No Comments

No Known Activations