INDEX

Explanations

mentions of specific numbers in a variety of contexts

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, particularly commas, indicating lists or additional information

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nai

-0.79

Els

-0.74

ains

-0.70

ain

-0.68

LIB

-0.66

Kay

-0.64

ç·

-0.60

inate

-0.60

sing

-0.59

inates

-0.59

POSITIVE LOGITS

 Mehran

0.70

rue

0.68

 respectively

0.64

osate

0.63

 âĵĺ

0.63

 partName

0.62

then

0.62

 chances

0.61

 Tsukuyomi

0.61

 nevertheless

0.61

Activations Density 0.570%

mentions of specific numbers in a variety of contexts

punctuation marks, particularly commas, indicating lists or additional information

No Comments

No Known Activations