INDEX

Explanations

mentions of negative trends or declines in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to various forms of decline in different contexts

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

":[{"

-0.69

bley

-0.69

ropri

-0.66

RA

-0.65

aptic

-0.63

Sources

-0.63

racuse

-0.62

Bet

-0.62

Ĭ

-0.61

iled

-0.59

POSITIVE LOGITS

cember

0.85

 attrition

0.77

lust

0.75

rates

0.73

 uranium

0.71

 precip

0.71

 rates

0.68

ftime

0.67

pend

0.67

lect

0.67

Activations Density 0.025%

mentions of negative trends or declines in various contexts

references to various forms of decline in different contexts

No Comments

No Known Activations