INDEX

Explanations

superlatives indicating something or someone as the most prominent or important

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the highest degree of something

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

rompt

-0.63

instead

-0.61

 Fist

-0.60

 Shepherd

-0.60

pload

-0.59

 CARD

-0.59

heid

-0.59

Ved

-0.58

 Processing

-0.57

 Nero

-0.56

POSITIVE LOGITS

 importantly

0.93

likely

0.91

 important

0.88

afa

0.81

 prominently

0.78

 likely

0.78

 prominent

0.77

 notable

0.76

 influential

0.75

 egregious

0.74

Activations Density 0.064%

superlatives indicating something or someone as the most prominent or important

phrases indicating the highest degree of something

No Comments

No Known Activations