INDEX

Explanations

phrases related to advertisements

oai_token-act-pair · gpt-3.5-turbo

references to advertisements

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

ĨĴ

-0.94

bred

-0.79

lihood

-0.77

-0.76

Jr

-0.73

 Caribbean

-0.71

 Dice

-0.69

 Cyprus

-0.69

otype

-0.68

ppo

-0.68

POSITIVE LOGITS

vertising

1.07

ads

1.00

verts

0.93

 advertising

0.89

strip

0.88

elaide

0.87

vertis

0.87

 nause

0.86

 billboards

0.82

ieu

0.82

Activations Density 0.021%

phrases related to advertisements

references to advertisements

No Comments

No Known Activations