INDEX

Explanations

phrases related to the Federal Reserve

oai_token-act-pair · gpt-3.5-turbo

references to federal entities or institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

IED

-0.83

paces

-0.74

::::::::

-0.72

vu

-0.68

sheets

-0.67

 Carbuncle

-0.65

utra

-0.64

onge

-0.64

boxes

-0.62

FUL

-0.62

POSITIVE LOGITS

 Reserve

1.27

ist

0.96

 Aviation

0.96

ists

0.91

 Bureau

0.89

 Election

0.89

istic

0.88

 Government

0.85

 Trade

0.84

 Communications

0.83

Activations Density 0.023%

phrases related to the Federal Reserve

references to federal entities or institutions

No Comments

No Known Activations