INDEX

Explanations

adjectives describing a situation or position

oai_token-act-pair · gpt-3.5-turbo

phrases indicating various states or conditions of being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MPG

-0.66

 Egyptians

-0.64

eni

-0.63

QL

-0.62

uristic

-0.62

bots

-0.60

 anonymously

-0.59

 Extensions

-0.59

 staples

-0.58

eous

-0.57

POSITIVE LOGITS

 limbo

1.07

 predicament

1.06

 hurry

1.04

 position

1.02

 orbit

0.90

 coma

0.89

 jeopardy

0.89

 precarious

0.88

shape

0.88

 danger

0.82

Activations Density 0.189%

adjectives describing a situation or position

phrases indicating various states or conditions of being

No Comments

No Known Activations