INDEX

Explanations

phrases related to commands or strong statements

oai_token-act-pair · gpt-3.5-turbo

punctuation marks and dialogue indicators in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Reviewer

-0.76

ĻĤ

-0.70

 faculties

-0.68

central

-0.66

 richness

-0.61

 misunder

-0.60

 experien

-0.60

ason

-0.60

 seeded

-0.60

udget

-0.58

POSITIVE LOGITS

 aloud

0.95

 goodbye

0.88

ß

0.82

enza

0.80

 chants

0.80

 mantra

0.79

/"

0.78

 motto

0.78

 stamped

0.77

Þ

0.77

Activations Density 0.311%

phrases related to commands or strong statements

punctuation marks and dialogue indicators in the text

No Comments

No Known Activations