INDEX

Explanations

comparative phrases indicating high levels of satisfaction or approval

oai_token-act-pair · gpt-3.5-turbo

expressions of degree or intensity, particularly relating to positive feelings or comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

hare

-0.70

apore

-0.69

tail

-0.68

wick

-0.65

hex

-0.62

reen

-0.61

ãĤ©

-0.61

izo

-0.59

oley

-0.59

 Daylight

-0.58

POSITIVE LOGITS

 than

0.74

nor

0.72

wcs

0.64

TPPStreamerBot

0.64

SPONSORED

0.64

>]

0.61

ONSORED

0.61

":["

0.60

 abundantly

0.60

 qualified

0.60

Activations Density 0.070%

comparative phrases indicating high levels of satisfaction or approval

expressions of degree or intensity, particularly relating to positive feelings or comparisons

No Comments

No Known Activations