INDEX

Explanations

occurrences of the word "more" followed by a quantity

oai_token-act-pair · gpt-3.5-turbo

references to an increasing quantity or number

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Gra

-0.76

ĺħ

-0.72

 Everywhere

-0.71

oes

-0.71

ISTER

-0.70

era

-0.69

onom

-0.66

fleet

-0.66

omed

-0.65

Hub

-0.65

POSITIVE LOGITS

 than

1.14

ado

0.95

 stringent

0.88

 elaborate

0.84

 installments

0.75

 sophisticated

0.74

 importantly

0.74

worldly

0.70

 advanced

0.70

 important

0.69

Activations Density 0.074%

occurrences of the word "more" followed by a quantity

references to an increasing quantity or number

No Comments

No Known Activations