INDEX

Explanations

mentions of nuclear reactors

oai_token-act-pair · gpt-3.5-turbo

references to nuclear reactors and their operational status

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

haw

-0.78

 Merrill

-0.73

 Agric

-0.70

alan

-0.69

words

-0.67

umbnail

-0.67

ãĤĭ

-0.66

assin

-0.66

boxing

-0.65

 Adams

-0.65

POSITIVE LOGITS

 reactors

1.05

 reactor

1.03

uclear

0.79

 irrad

0.74

utonium

0.74

ptions

0.73

 uranium

0.73

 Fukushima

0.71

 accidents

0.71

 radiation

0.70

Activations Density 0.035%

mentions of nuclear reactors

references to nuclear reactors and their operational status

No Comments

No Known Activations