INDEX

Explanations

words related to technological advancements and progress

oai_token-act-pair · gpt-3.5-turbo

mentions of development processes in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

zzi

-0.83

pload

-0.78

Ago

-0.69

Ń·

-0.68

mic

-0.65

pper

-0.64

ca

-0.64

kowski

-0.64

aternity

-0.61

zer

-0.60

POSITIVE LOGITS

 development

0.88

ivism

0.83

Development

0.83

 ende

0.79

ogue

0.77

development

0.73

venture

0.72

cember

0.72

 agre

0.72

yout

0.70

Activations Density 0.024%

words related to technological advancements and progress

mentions of development processes in various contexts

No Comments

No Known Activations