INDEX

Explanations

terms related to attributes or qualities such as being "ridden", "grade", "based", "sponsored", "smelling", "owned", "free", "long", "winning", "negative", "positive", "propelled", "grade", "negative", "propelled", "

oai_token-act-pair · gpt-3.5-turbo

terms related to business and organizational operations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

elcome

-0.80

veyard

-0.77

hner

-0.74

ÄŁ

-0.74

conn

-0.73

gotten

-0.72

 Downs

-0.71

Arm

-0.70

 Clause

-0.69

idelines

-0.69

POSITIVE LOGITS

 olds

0.87

 entertainment

0.74

 guest

0.70

 event

0.70

 enterprise

0.69

 ones

0.68

 super

0.68

itiz

0.68

 educational

0.67

rency

0.67

Activations Density 0.303%

terms related to attributes or qualities such as being "ridden", "grade", "based", "sponsored", "smelling", "owned", "free", "long", "winning", "negative", "positive", "propelled", "grade", "negative", "propelled", "

terms related to business and organizational operations

No Comments

No Known Activations