INDEX

Explanations

words related to the utilization of something

oai_token-act-pair · gpt-3.5-turbo

the term "uses" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Patri

-0.67

SPONSORED

-0.67

Hai

-0.65

 Buff

-0.63

 Gulf

-0.63

AIDS

-0.63

 Braz

-0.62

 Hurricanes

-0.62

 Parad

-0.61

 Empires

-0.61

POSITIVE LOGITS

paces

1.01

 uses

0.85

ettings

0.84

ãĥ¼ãĥĨãĤ£

0.83

poons

0.83

ancies

0.82

uristic

0.81

fully

0.80

afety

0.79

uggest

0.76

Activations Density 0.011%

words related to the utilization of something

the term "uses" in various contexts

No Comments

No Known Activations