INDEX

Explanations

phrases or words that signal a shift in focus or importance in a sentence or paragraph

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing importance or significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

fell

-0.66

itely

-0.63

ebin

-0.62

prus

-0.61

lopp

-0.61

selection

-0.61

brook

-0.60

uum

-0.58

tones

-0.57

uld

-0.57

POSITIVE LOGITS

 importantly

0.87

 âĢ

0.77

0.72

ï¸ı

0.71

:'

0.70

,...

0.70

,.

0.69

âĢ

0.66

Ù

0.66

 though

0.65

Activations Density 0.101%

phrases or words that signal a shift in focus or importance in a sentence or paragraph

phrases emphasizing importance or significance

No Comments

No Known Activations