INDEX

Explanations

descriptions of content or events

oai_token-act-pair · gpt-3.5-turbo

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

nesty

-0.80

lycer

-0.79

protection

-0.78

)]

-0.77

argument

-0.70

 Prediction

-0.68

 Explan

-0.68

 blaming

-0.67

PsyNetMessage

-0.67

due

-0.67

POSITIVE LOGITS

 classics

1.01

 eras

0.94

 landmarks

0.92

 iconic

0.90

 celebrities

0.86

 landscapes

0.85

 unforgettable

0.85

 contemporary

0.84

 genres

0.84

 continents

0.84

Activations Density 0.776%

descriptions of content or events

No Comments

No Known Activations