INDEX

Explanations

the word "view" or related terms

oai_token-act-pair · gpt-3.5-turbo

references to differing perspectives or interpretations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

foreseen

-0.86

ciating

-0.76

ccoli

-0.73

quished

-0.73

ertodd

-0.71

ividual

-0.69

 Parenthood

-0.68

rha

-0.68

ãģį

-0.67

 Lumpur

-0.67

POSITIVE LOGITS

 view

0.91

 viewpoint

0.91

 prevailing

0.83

 worldview

0.78

ologies

0.77

 views

0.73

 interpretation

0.73

 doctrine

0.68

 interpretations

0.67

 favored

0.67

Activations Density 0.217%

the word "view" or related terms

references to differing perspectives or interpretations

No Comments

No Known Activations