INDEX

Explanations

percentage figures related to approval ratings

oai_token-act-pair · gpt-3.5-turbo

references to approval ratings and public opinion surveys

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Cooke

-0.74

 Lump

-0.69

Ley

-0.68

 specialization

-0.67

lla

-0.67

 Nano

-0.67

 nano

-0.67

aer

-0.66

 Daly

-0.63

axies

-0.63

POSITIVE LOGITS

 ratings

1.31

 rating

1.20

Rating

1.05

 Gallup

1.01

renheit

0.98

rating

0.98

 Ratings

0.94

 disapprove

0.91

 Rating

0.88

rated

0.86

Activations Density 0.092%

percentage figures related to approval ratings

references to approval ratings and public opinion surveys

No Comments

No Known Activations