INDEX

Explanations

the word "of" followed by a numeric value or a pronoun

oai_token-act-pair · gpt-3.5-turbo

references to fractions or percentages, particularly focusing on "half" and its related contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arella

-0.70

AMI

-0.65

 exagger

-0.63

affer

-0.62

acus

-0.61

abilia

-0.60

 grouping

-0.60

 blur

-0.60

 palp

-0.59

hof

-0.58

POSITIVE LOGITS

 Sevent

0.77

 respondents

0.73

ths

0.69

pees

0.62

 dozen

0.62

nir

0.61

 Americans

0.60

 households

0.59

 America

0.59

OUR

0.59

Activations Density 0.063%

the word "of" followed by a numeric value or a pronoun

references to fractions or percentages, particularly focusing on "half" and its related contexts

No Comments

No Known Activations