INDEX

Explanations

phrases related to economic indicators or terms used in economic contexts

oai_token-act-pair · gpt-3.5-turbo

terms related to economic indicators and health conditions

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

FUL

-0.81

pedia

-0.78

uku

-0.73

ueless

-0.72

,,,,

-0.71

ynt

-0.70

ounced

-0.70

HOU

-0.69

hess

-0.68

town

-0.68

POSITIVE LOGITS

 comprom

0.74

 Computing

0.71

 disorder

0.71

 metic

0.64

 Integrated

0.63

 intermedi

0.62

 identification

0.60

 Disorder

0.60

 disability

0.59

alpha

0.59

Activations Density 0.347%

phrases related to economic indicators or terms used in economic contexts

terms related to economic indicators and health conditions

No Comments

No Known Activations