INDEX

Explanations

words related to enhancement or improvement

oai_token-act-pair · gpt-3.5-turbo

terms related to enhancement or improvements 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

Negative Logits

geist

-0.72

 Phant

-0.70

 Sakuya

-0.67

 Owner

-0.66

 Origin

-0.65

 Fired

-0.65

HIP

-0.64

 parent

-0.63

 Orbit

-0.63

POSITIVE LOGITS

anced

1.38

enh

1.32

ancing

1.29

urst

0.99

ancers

0.93

inkle

0.90

ishment

0.89

 subsequ

0.88

ancer

0.85

ofer

0.84

Activations Density 0.007%

words related to enhancement or improvement

terms related to enhancement or improvements in various contexts

No Known Activations