INDEX

Explanations

phrases that mention the word "both" followed by some common theme or concept

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "both" in various contexts

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

uably

-0.81

 nowhere

-0.76

naire

-0.73

ļ

-0.71

lied

-0.70

odore

-0.68

uable

-0.67

din

-0.67

 WATCHED

-0.67

ertodd

-0.67

POSITIVE LOGITS

 sexes

1.74

 sides

1.51

 genders

1.49

 halves

1.34

 parties

1.04

 Houses

0.98

 extremes

0.97

 coasts

0.96

 ends

0.93

 directions

0.85

Activations Density 0.059%

phrases that mention the word "both" followed by some common theme or concept

references to the concept of "both" in various contexts

No Comments

No Known Activations