INDEX

Explanations

phrases related to legal or governmental contexts, particularly involving federal matters

oai_token-act-pair · gpt-3.5-turbo

references to federal institutions or government actions

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

enger

-0.91

lihood

-0.85

sbm

-0.80

Maker

-0.80

Dog

-0.79

zzo

-0.76

bringer

-0.76

 Clever

-0.75

pered

-0.74

 Canary

-0.74

POSITIVE LOGITS

 agencies

1.00

 appellate

0.99

 government

0.98

 agency

0.93

 authorities

0.89

 oversight

0.88

 dollars

0.86

 officials

0.86

 jurisdiction

0.85

 bureaucracy

0.85

Activations Density 0.028%

phrases related to legal or governmental contexts, particularly involving federal matters

references to federal institutions or government actions

No Comments

No Known Activations