INDEX

Explanations

references to medical and health-related terms, including medication, injuries, and physical conditions

oai_token-act-pair · gpt-3.5-turbo

the word "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

IFA

-0.65

âĢł

-0.61

IDA

-0.59

 Germany

-0.59

oslov

-0.59

 today

-0.59

 Communism

-0.58

Conn

-0.58

 Valve

-0.58

POSITIVE LOGITS

 occasional

1.14

 heaviest

1.01

 slightest

0.99

 usual

0.97

 aforementioned

0.95

 simplest

0.94

 ubiquitous

0.93

ses

0.93

 possibility

0.92

 entirety

0.92

Activations Density 0.479%

references to medical and health-related terms, including medication, injuries, and physical conditions

the word "the."

No Comments

No Known Activations