INDEX

Explanations

proper nouns or names mentioned in a context of importance or relevance

oai_token-act-pair · gpt-3.5-turbo

phrases indicating identification or categorization

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

width

-0.67

amphetamine

-0.65

Length

-0.64

itiveness

-0.64

Plex

-0.64

length

-0.64

raq

-0.61

ãĥ¥

-0.61

auldron

-0.61

ecd

-0.60

POSITIVE LOGITS

 follows

1.07

pires

0.93

criptions

0.91

ĪĴ

0.87

 soon

0.87

pired

0.84

 opposed

0.83

 belonging

0.82

phy

0.80

bestos

0.79

Activations Density 0.153%

proper nouns or names mentioned in a context of importance or relevance

phrases indicating identification or categorization

No Comments

No Known Activations