INDEX

Explanations

phrases related to background information or checks

oai_token-act-pair · gpt-3.5-turbo

references to background checks

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

erion

-0.78

nard

-0.76

ikh

-0.76

nia

-0.69

icular

-0.69

 ILCS

-0.68

 WATCHED

-0.68

enberg

-0.67

ora

-0.67

eah

-0.67

POSITIVE LOGITS

 checks

0.89

 noise

0.87

coat

0.78

 check

0.76

 Checks

0.76

 radiation

0.75

 background

0.75

spection

0.73

 backgrounds

0.71

 chatter

0.69

Activations Density 0.061%

phrases related to background information or checks

references to background checks

No Comments

No Known Activations