INDEX

Explanations

sudden or unexpected changes or actions in events or people

oai_token-act-pair · gpt-3.5-turbo

words related to sudden or unexpected changes or events

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

arium

-0.81

itaire

-0.79

aries

-0.79

ipeg

-0.75

cius

-0.71

ified

-0.70

naire

-0.69

emark

-0.68

abulary

-0.68

maid

-0.67

POSITIVE LOGITS

è¦

0.84

doms

0.70

 abruptly

0.66

 predec

0.65

rent

0.65

awa

0.65

llor

0.64

é¾

0.64

 blocker

0.63

lder

0.62

Activations Density 0.030%

sudden or unexpected changes or actions in events or people

words related to sudden or unexpected changes or events

No Comments

No Known Activations