INDEX

Explanations

names of people involved in the production or editing of a piece of content

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

 resil

-0.77

 trou

-0.67

 helicop

-0.64

 psychiat

-0.64

ront

-0.63

ologically

-0.62

 unnecess

-0.62

agic

-0.61

ovy

-0.60

stration

-0.60

POSITIVE LOGITS

-)

1.15

alias

0.90

 alternatively

0.86

âĢ¢âĢ¢âĢ¢âĢ¢

0.86

âĢ¢âĢ¢

0.78

cf

0.75

 Editing

0.74

 thence

0.72

escription

0.71

IFF

0.65

Activations Density 0.043%

names of people involved in the production or editing of a piece of content

No Comments

No Known Activations