INDEX

Explanations

verbs and adjectives related to attributes or actions that are definitive or causative in some way

oai_token-act-pair · gpt-3.5-turbo

instances of the verb "to be" in various forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ruct

-0.73

adelphia

-0.64

cess

-0.64

 Radius

-0.63

ãĤ´ãĥ³

-0.63

ization

-0.61

 Souls

-0.60

MSN

-0.58

iasco

-0.57

 Warcraft

-0.57

POSITIVE LOGITS

 therefore

1.29

 consequently

1.27

 accordingly

1.14

 thus

0.96

 furthermore

0.94

 thereby

0.88

 subsequently

0.79

 moreover

0.78

 thereafter

0.76

 consequ

0.75

Activations Density 0.205%

verbs and adjectives related to attributes or actions that are definitive or causative in some way

instances of the verb "to be" in various forms

No Comments

No Known Activations