INDEX

Explanations

proper nouns of individuals

oai_token-act-pair · gpt-3.5-turbo

references to individuals or characters in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Bound

-0.75

 Anything

-0.67

 VIDEOS

-0.66

 Around

-0.65

BACK

-0.65

 Checking

-0.64

ÂłÂłÂłÂł

-0.64

 Delicious

-0.63

 Basics

-0.62

 Doctrine

-0.62

POSITIVE LOGITS

oping

1.09

 accompanies

1.08

soever

0.99

oped

0.97

 preceded

0.96

 frequ

0.95

 attends

0.95

 resided

0.93

 oversaw

0.90

 overcame

0.89

Activations Density 0.153%

proper nouns of individuals

references to individuals or characters in a narrative context

No Comments

No Known Activations