INDEX

Explanations

mentions of the word "federal" in the text

oai_token-act-pair · gpt-3.5-turbo

references to federal government or federal laws

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

lihood

-0.98

enger

-0.87

sbm

-0.84

zzo

-0.84

 Clever

-0.78

Wo

-0.77

 Rooms

-0.76

Dog

-0.75

bringer

-0.75

Maker

-0.74

POSITIVE LOGITS

 agencies

1.02

 appellate

1.00

 government

0.98

 agency

0.95

law

0.90

 authorities

0.90

 oversight

0.88

ized

0.88

 jurisdiction

0.88

 officials

0.87

Activations Density 0.028%

mentions of the word "federal" in the text

references to federal government or federal laws

No Comments

No Known Activations