INDEX

Explanations

references to diesel fuel

oai_token-act-pair · gpt-3.5-turbo

terms related to diesel fuel and its prices

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

xual

-1.07

olulu

-0.95

yip

-0.92

ĸļ

-0.81

odore

-0.79

onew

-0.78

 skelet

-0.77

uckland

-0.72

ĺħ

-0.72

 Kinnikuman

-0.71

POSITIVE LOGITS

punk

1.04

 fumes

0.98

jet

0.89

 diesel

0.83

 fuel

0.81

 exhaust

0.79

GH

0.75

 emissions

0.73

 emission

0.73

minist

0.71

Activations Density 0.013%

references to diesel fuel

terms related to diesel fuel and its prices

No Comments

No Known Activations