INDEX

Explanations

keywords related to specific universities, specifically focusing on Rutgers and Baylor

oai_token-act-pair · gpt-3.5-turbo

mentions of specific universities and colleges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

acl

-0.65

DonaldTrump

-0.65

judicial

-0.62

othy

-0.62

complex

-0.61

cy

-0.61

udic

-0.61

 detached

-0.60

 deprivation

-0.60

 fict

-0.60

POSITIVE LOGITS

 Haram

1.06

mson

1.02

 Baylor

1.00

 Libraries

0.91

 University

0.87

 Univ

0.84

©¶æ¥µ

0.82

 Instruments

0.81

 Rutgers

0.78

keyes

0.77

Activations Density 0.014%

keywords related to specific universities, specifically focusing on Rutgers and Baylor

mentions of specific universities and colleges

No Comments

No Known Activations