INDEX

Explanations

phrases related to advice or things to consider

oai_token-act-pair · gpt-3.5-turbo

words and phrases indicating considerations or actions to be taken

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

quickShipAvailable

-0.67

 Transcript

-0.65

ergy

-0.61

VO

-0.61

ICLE

-0.61

Va

-0.56

NM

-0.56

 functioning

-0.55

nexus

-0.55

Jav

-0.55

POSITIVE LOGITS

 beware

0.99

 aspire

0.97

 cherish

0.92

 ponder

0.85

 behold

0.85

 strive

0.81

 celebrate

0.80

 pity

0.79

 consider

0.78

 envy

0.77

Activations Density 0.132%

phrases related to advice or things to consider

words and phrases indicating considerations or actions to be taken

No Comments

No Known Activations