INDEX

Explanations

specific references to locations or organizations in relation to individuals

oai_token-act-pair · gpt-3.5-turbo

occurrences of 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

SPONSORED

-0.81

\'

-0.70

strap

-0.68

 resembles

-0.68

izes

-0.63

 persists

-0.62

 resides

-0.62

 illustrates

-0.61

udder

-0.61

âĢł

-0.61

POSITIVE LOGITS

 same

1.19

 entirety

1.05

 aforementioned

0.99

 latter

0.96

 forefront

0.92

 highest

0.91

 exact

0.87

ocratic

0.86

 proverbial

0.86

 entire

0.85

Activations Density 1.111%

specific references to locations or organizations in relation to individuals

occurrences of the word "the."

No Comments

No Known Activations