INDEX

Explanations

phrases or sentences instructing or encouraging the use of something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "use" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

hoff

-0.69

watching

-0.67

ansion

-0.63

woman

-0.62

ikhail

-0.61

Enlarge

-0.60

pton

-0.60

si

-0.60

hra

-0.59

iae

-0.59

POSITIVE LOGITS

fully

1.16

FUL

1.00

ful

0.94

 condoms

0.90

 aliases

0.87

 sparing

0.84

fulness

0.83

 caution

0.79

 contraceptives

0.77

 whichever

0.77

Activations Density 0.124%

phrases or sentences instructing or encouraging the use of something

instances of the word "use" and its variations in different contexts

No Comments

No Known Activations