INDEX

Explanations

descriptions of numbers, quantities, and statistics

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

soType

-0.67

 miscon

-0.62

 horm

-0.61

ppe

-0.60

 customization

-0.60

 considerations

-0.59

 localization

-0.59

 backstage

-0.59

 directions

-0.58

 concepts

-0.57

POSITIVE LOGITS

 total

1.25

 whopping

1.14

1.13

 averaged

1.12

1.11

1.10

Activations Density 1.193%

descriptions of numbers, quantities, and statistics

No Comments

No Known Activations