INDEX

Explanations

punctuation marks indicating emphasis or separation

oai_token-act-pair · gpt-3.5-turbo

references to health-related topics

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

vim

-0.68

soDeliveryDate

-0.66

iatus

-0.66

icho

-0.63

irect

-0.62

ilty

-0.61

ctions

-0.61

ct

-0.58

+/-

-0.58

nesty

-0.58

POSITIVE LOGITS

Secondly

0.73

!]

0.69

 Secondly

0.68

 actively

0.66

aukee

0.65

paces

0.62

],"

0.61

];

0.60

 ALSO

0.60

also

0.60

Activations Density 0.261%

punctuation marks indicating emphasis or separation

references to health-related topics

No Comments

No Known Activations