INDEX

Explanations

phrases related to the U.S. Federal Government and its agencies

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Federal"

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

-0.81

onge

-0.77

pered

-0.74

 Clever

-0.72

paces

-0.72

ammers

-0.72

âĹ¼

-0.71

vier

-0.70

Downloadha

-0.70

enger

-0.70

POSITIVE LOGITS

 Reserve

1.10

ist

0.87

ists

0.86

 Bureau

0.83

 Election

0.82

 Aviation

0.79

 Credit

0.79

 Institution

0.78

 Government

0.77

 Communications

0.77

Activations Density 0.013%

phrases related to the U.S. Federal Government and its agencies

occurrences of the word "Federal"

No Comments

No Known Activations