INDEX

Explanations

pronouns 'who' referring to a group of individuals

oai_token-act-pair · gpt-3.5-turbo

the pronoun "who," indicating a focus on individuals or groups being referenced

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

 Anything

-0.75

 Anyway

-0.73

 Delicious

-0.69

Rest

-0.69

 Bound

-0.69

ÂłÂłÂłÂł

-0.69

BACK

-0.64

PokÃ©

-0.62

 Basics

-0.62

 Recovery

-0.62

POSITIVE LOGITS

oping

1.12

oped

1.01

soever

0.99

 preceded

0.97

 specialize

0.96

 migrated

0.93

ppers

0.90

ever

0.89

 resided

0.89

 participated

0.87

Activations Density 0.136%

pronouns 'who' referring to a group of individuals

the pronoun "who," indicating a focus on individuals or groups being referenced

No Comments

No Known Activations