INDEX

Explanations

instances of the word "North Carolina."

oai_token-act-pair · gpt-3.5-turbo

instances and mentions of "North Carolina."

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

lords

-0.80

Lens

-0.79

bats

-0.78

alty

-0.77

shake

-0.76

matically

-0.76

uably

-0.76

sch

-0.73

sett

-0.73

gerald

-0.71

POSITIVE LOGITS

 Hurricanes

0.95

 State

0.90

olina

0.90

urses

0.90

 Carolina

0.89

 Courage

0.89

 Herrera

0.83

sylvania

0.81

 Edison

0.81

ļéĨĴ

0.80

Activations Density 0.014%

instances of the word "North Carolina."

instances and mentions of "North Carolina."

No Comments

No Known Activations