INDEX

Explanations

references to the location "Ag" or phrases related to it

oai_token-act-pair · gpt-3.5-turbo

the term "Ag" or variations related to a specific location or entity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Dare

-0.83

 Hurricanes

-0.81

 Jenner

-0.79

FORMATION

-0.77

Reloaded

-0.73

ãĥīãĥ©ãĤ´ãĥ³

-0.72

OCK

-0.69

ãĥĥãĤ¯

-0.68

 Musk

-0.67

OPLE

-0.66

POSITIVE LOGITS

reements

1.19

reement

1.06

nostic

1.03

raf

1.00

encies

0.94

rog

0.94

ree

0.94

uve

0.93

endas

0.92

rig

0.92

Activations Density 0.005%

references to the location "Ag" or phrases related to it

the term "Ag" or variations related to a specific location or entity

No Comments

No Known Activations