INDEX

Explanations

locations or entities related to the term "ford"

oai_token-act-pair · gpt-3.5-turbo

mentions of specific geographical locations, particularly those ending in 'ford'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Magikarp

-0.88

ntil

-0.81

ngth

-0.79

Arab

-0.70

undown

-0.69

letal

-0.68

verages

-0.67

acca

-0.67

 drink

-0.66

undo

-0.65

POSITIVE LOGITS

shire

1.78

wall

0.90

hurst

0.83

ford

0.78

doms

0.78

erers

0.77

bats

0.77

erer

0.76

erences

0.75

gate

0.74

Activations Density 0.022%

locations or entities related to the term "ford"

mentions of specific geographical locations, particularly those ending in 'ford'

No Comments

No Known Activations