INDEX

Explanations

phrases starting with "the" followed by additional information or context

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pers

-0.90

.","

-0.79

antes

-0.73

 thereby

-0.68

tec

-0.67

 somehow

-0.66

.(

-0.66

etooth

-0.65

ãĤ¹ãĥĪ

-0.65

soever

-0.65

POSITIVE LOGITS

 latter

1.05

 aforementioned

0.97

 emergence

0.92

 simplest

0.91

 foregoing

0.90

 onset

0.90

 same

0.87

 latest

0.85

 advent

0.84

 outbreak

0.81

Activations Density 0.307%

phrases starting with "the" followed by additional information or context

occurrences of the word "the"

No Comments

No Known Activations