INDEX

Explanations

phrases with adjectives and adverbs indicating intensity or comparison

oai_token-act-pair · gpt-3.5-turbo

intensifiers and degree modifiers that emphasize qualities or characteristics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

liest

-0.90

cius

-0.78

ciating

-0.77

bringing

-0.76

ickr

-0.75

_.

-0.71

onnaissance

-0.71

ulia

-0.70

 Bearing

-0.69

ring

-0.68

POSITIVE LOGITS

 quaint

0.84

 alike

0.82

 cozy

0.81

 futuristic

0.80

 smug

0.80

 ominous

0.80

 feminine

0.79

 comfortable

0.79

 alien

0.79

 normal

0.78

Activations Density 0.103%

phrases with adjectives and adverbs indicating intensity or comparison

intensifiers and degree modifiers that emphasize qualities or characteristics

No Comments

No Known Activations