INDEX

Explanations

words related to glorification and gratification

oai_token-act-pair · gpt-3.5-turbo

words related to glorification and gratitude, often in a critical or contentious context

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

ħĭ

-0.76

 miscarriage

-0.75

 away

-0.68

 Unch

-0.68

 Avalon

-0.67

 Pants

-0.67

 Spice

-0.66

 Wonderland

-0.66

 Away

-0.66

 inclination

-0.64

POSITIVE LOGITS

ifying

2.24

ified

2.21

ification

2.02

ifications

1.92

ifiers

1.89

ifiable

1.88

ifier

1.87

ifies

1.86

ific

1.73

uitous

1.57

Activations Density 0.060%

words related to glorification and gratification

words related to glorification and gratitude, often in a critical or contentious context

No Comments

No Known Activations