INDEX

Explanations

terms related to the concept of "regular."

oai_token-act-pair · gpt-3.5-turbo

the concept of regularity or consistency in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Sov

-0.80

IDA

-0.80

UST

-0.73

lda

-0.70

Cub

-0.70

ï¸ı

-0.69

 Specific

-0.68

 Related

-0.68

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

-0.68

FG

-0.67

POSITIVE LOGITS

ised

1.03

ity

1.00

isation

0.96

isations

0.91

ises

0.91

etheless

0.87

cy

0.86

isers

0.83

uation

0.82

ization

0.82

Activations Density 0.009%

terms related to the concept of "regular."

the concept of regularity or consistency in various contexts

No Comments

No Known Activations