INDEX

Explanations

references to various types of production and energy-related words

oai_token-act-pair · gpt-3.5-turbo

terms related to production and output, especially in environmental and economic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Parent

-0.78

laus

-0.70

 Customs

-0.67

 Juda

-0.66

uthor

-0.65

ç¥ŀ

-0.63

 Practices

-0.63

 Username

-0.62

mate

-0.61

DIT

-0.61

POSITIVE LOGITS

 usable

0.94

 quantities

0.83

loads

0.75

 viable

0.73

ilibrium

0.73

 greenhouse

0.73

cible

0.73

 useful

0.72

actory

0.72

 antibodies

0.71

Activations Density 0.278%

references to various types of production and energy-related words

terms related to production and output, especially in environmental and economic contexts

No Comments

No Known Activations