INDEX

Explanations

information related to programming errors or code snippets in a text

oai_token-act-pair · gpt-3.5-turbo

elements related to significant medical terms and health-related concepts

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

?]

-0.62

rez

-0.57

etheless

-0.55

 Loch

-0.55

 Ukip

-0.55

 Chau

-0.54

doms

-0.54

 Wong

-0.54

 Centauri

-0.53

Beg

-0.52

POSITIVE LOGITS

 allocate

0.55

 evaluates

0.55

cycles

0.52

bilt

0.51

 respectively

0.50

erenn

0.48

entimes

0.46

 classify

0.46

 evaluate

0.45

 utilizes

0.45

Activations Density 1.857%

information related to programming errors or code snippets in a text

elements related to significant medical terms and health-related concepts

No Comments

No Known Activations