INDEX

Explanations

organizations and institutions involved in policy research and analysis

oai_token-act-pair · gpt-3.5-turbo

references to think tanks and policy analysis organizations

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

Ò

-0.71

ardless

-0.70

abiding

-0.69

GBT

-0.69

 stret

-0.66

 jerseys

-0.64

ABE

-0.64

 puberty

-0.63

cream

-0.63

 transporter

-0.62

POSITIVE LOGITS

 Brookings

0.91

 scholar

0.89

 analyst

0.86

 economist

0.85

 analytic

0.85

 Institute

0.84

 economists

0.83

Brook

0.81

 RAND

0.79

 analysts

0.79

Activations Density 0.260%

organizations and institutions involved in policy research and analysis

references to think tanks and policy analysis organizations

No Comments

No Known Activations