INDEX

Explanations

phrases related to peace of mind

oai_token-act-pair · gpt-3.5-turbo

phrases related to "peace of mind."

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

arro

-0.90

matically

-0.63

vernment

-0.63

Downloadha

-0.62

eor

-0.60

allel

-0.59

ival

-0.59

 objectionable

-0.59

fin

-0.58

 trash

-0.58

POSITIVE LOGITS

 knowing

0.95

 lions

0.65

wart

0.64

warts

0.63

 assured

0.62

thy

0.61

ourt

0.59

mind

0.59

 hearts

0.58

 mind

0.57

Activations Density 0.179%

phrases related to peace of mind

phrases related to "peace of mind."

No Comments

No Known Activations