INDEX

Explanations

comparisons and measurements between different entities

oai_token-act-pair · gpt-3.5-turbo

phrases indicating comparisons or contrasts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ANCE

-0.76

hardt

-0.73

iband

-0.72

shire

-0.67

Bad

-0.66

Premium

-0.65

*/(

-0.65

arna

-0.64

assian

-0.64

colo

-0.62

POSITIVE LOGITS

 usual

0.93

 ours

0.81

 previous

0.81

 traditional

0.74

 those

0.74

 other

0.73

 actual

0.71

 customary

0.69

 peers

0.69

 comparable

0.68

Activations Density 0.062%

comparisons and measurements between different entities

phrases indicating comparisons or contrasts

No Comments

No Known Activations