INDEX

Explanations

phrases related to things being full or filled with something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "filled" and its variations, indicating contexts involving abundance or fullness

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

LM

-0.67

Norm

-0.67

andum

-0.66

appro

-0.66

 isolate

-0.64

Hill

-0.64

isation

-0.64

utan

-0.64

nature

-0.63

rf

-0.63

POSITIVE LOGITS

 brim

0.78

gling

0.74

eals

0.72

erness

0.72

 overflowing

0.70

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

0.69

ardless

0.67

uding

0.67

usion

0.66

 orbs

0.65

Activations Density 0.036%

phrases related to things being full or filled with something

instances of the word "filled" and its variations, indicating contexts involving abundance or fullness

No Comments

No Known Activations