INDEX

Explanations

phrases related to official statements or announcements

oai_token-act-pair · gpt-3.5-turbo

references to formal statements or announcements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

upiter

-0.90

avorite

-0.79

existent

-0.79

rys

-0.78

elsius

-0.72

cephal

-0.72

estern

-0.70

cffff

-0.70

opes

-0.69

rowd

-0.68

POSITIVE LOGITS

 statement

1.13

Statement

0.97

 statements

0.95

 warr

0.93

soType

0.85

gow

0.82

 encour

0.76

 Statement

0.75

ariat

0.74

 goodbye

0.73

Activations Density 0.035%

phrases related to official statements or announcements

references to formal statements or announcements

No Comments

No Known Activations