INDEX

Explanations

settings or configurations related to different modes

oai_token-act-pair · gpt-3.5-turbo

different variations of "mode" in the context of functionalities or settings

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

enegger

-0.84

mony

-0.75

owan

-0.73

roma

-0.72

 Beir

-0.69

bones

-0.69

 Aires

-0.67

ertodd

-0.67

iannopoulos

-0.67

ingly

-0.66

POSITIVE LOGITS

etting

0.80

 upgr

0.75

 selector

0.71

quit

0.68

 Shift

0.68

ounce

0.67

zees

0.65

 mode

0.64

 parity

0.64

 enabled

0.62

Activations Density 0.019%

settings or configurations related to different modes

different variations of "mode" in the context of functionalities or settings

No Comments

No Known Activations