INDEX

Explanations

phrases indicating a current stage of activity or progress

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 boobs

-0.68

 Soldiers

-0.67

 Sands

-0.65

by

-0.64

 BaseType

-0.64

»Ĵ

-0.63

gans

-0.59

bey

-0.58

ById

-0.58

 Pixie

-0.57

POSITIVE LOGITS

ching

1.11

 talks

1.04

 charge

0.96

 discussions

0.94

 unch

0.90

 negotiations

0.90

 agreement

0.89

 touch

0.89

 favor

0.89

 contention

0.88

Activations Density 0.089%

phrases indicating a current stage of activity or progress

No Comments

No Known Activations