INDEX

Explanations

phrases related to specific locations or events, particularly those involving the term "Co"

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of a specific location or entity identified as "Co."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

lihood

-0.85

 Halls

-0.70

 GOODMAN

-0.68

 corpus

-0.67

 IMAGES

-0.66

 concess

-0.58

 Yanuk

-0.58

RTX

-0.58

 bankruptcy

-0.57

 NOTICE

-0.57

POSITIVE LOGITS

oley

1.25

opers

1.19

efficient

1.17

efficients

1.16

herent

1.16

aching

1.16

venants

1.15

ppers

1.12

existence

1.11

ffe

1.10

Activations Density 0.020%

phrases related to specific locations or events, particularly those involving the term "Co"

repeated mentions of a specific location or entity identified as "Co."

No Comments

No Known Activations