INDEX

Explanations

the word "was" occurring frequently in sentences

oai_token-act-pair · gpt-3.5-turbo

the verb "was" in various contexts, indicating past events or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Compare

-0.64

 IMAGES

-0.63

bys

-0.62

stood

-0.60

veland

-0.60

 Horizons

-0.60

 Supports

-0.60

Footnote

-0.59

 Extend

-0.58

 Mountains

-0.57

POSITIVE LOGITS

wolves

1.23

hes

1.19

nt

1.07

wolf

1.01

 conceived

0.94

 born

0.91

 originally

0.91

 supposed

0.90

 able

0.88

 destined

0.88

Activations Density 0.459%

the word "was" occurring frequently in sentences

the verb "was" in various contexts, indicating past events or states

No Comments

No Known Activations