INDEX

Explanations

words related to capabilities or features

oai_token-act-pair · gpt-3.5-turbo

words related to abilities or features of systems and technologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

paying

-0.72

eree

-0.71

birth

-0.71

edi

-0.70

inos

-0.69

cus

-0.66

wind

-0.66

aternity

-0.64

ograph

-0.62

ablo

-0.62

POSITIVE LOGITS

 capabilities

0.98

 capability

0.89

hered

0.81

auga

0.77

abilities

0.73

ibilities

0.72

xes

0.70

ilities

0.70

kinson

0.69

yip

0.69

Activations Density 0.021%

words related to capabilities or features

words related to abilities or features of systems and technologies

No Comments

No Known Activations