INDEX

Explanations

prepositions 'in' and 'around'

oai_token-act-pair · gpt-3.5-turbo

the repetitive use of the word "and" to denote connections or relationships in the text

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

puting

-0.65

 DRAGON

-0.64

RPG

-0.63

 Doodle

-0.62

 Nerd

-0.61

 Dynam

-0.61

Times

-0.58

Nin

-0.58

 Primordial

-0.58

SPA

-0.57

POSITIVE LOGITS

rogen

1.23

rogens

1.15

romeda

0.86

nery

0.81

rew

0.80

oh

0.68

 annexed

0.67

alus

0.66

chard

0.66

rology

0.64

Activations Density 0.121%

prepositions 'in' and 'around'

the repetitive use of the word "and" to denote connections or relationships in the text

No Comments

No Known Activations