INDEX

Explanations

phrases related to ongoing events or situations

oai_token-act-pair · gpt-3.5-turbo

references to current events or situations happening in specific locations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ealous

-0.82

icult

-0.79

essor

-0.74

inction

-0.74

killed

-0.71

inctions

-0.69

¤

-0.68

ulnerability

-0.67

Increases

-0.66

ilege

-0.65

POSITIVE LOGITS

 Vegas

0.96

effic

0.91

 Cleveland

0.87

 Baltimore

0.87

between

0.86

 Wester

0.86

 Syria

0.84

 regards

0.84

 front

0.83

 downtown

0.82

Activations Density 0.294%

phrases related to ongoing events or situations

references to current events or situations happening in specific locations

No Comments

No Known Activations