INDEX

Explanations

the term "observer" or its variations in sentences

oai_token-act-pair · gpt-3.5-turbo

references to individuals observing events or situations

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

Ingredients

-0.71

eways

-0.70

ten

-0.69

Enough

-0.67

eating

-0.66

Hom

-0.64

ahime

-0.64

yrics

-0.61

Customer

-0.61

Percent

-0.60

POSITIVE LOGITS

 observer

1.11

 observers

1.06

wat

0.87

opol

0.86

 observing

0.82

auts

0.73

 Observer

0.73

 rejoice

0.71

hower

0.70

 blinded

0.70

Activations Density 0.026%

the term "observer" or its variations in sentences

references to individuals observing events or situations

No Comments

No Known Activations