INDEX

Explanations

phrases indicating a comparison or relationship between different entities or concepts

oai_token-act-pair · gpt-3.5-turbo

the word "the" and its variations in different contexts

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

 Canaver

-0.78

ourney

-0.75

%%%%

-0.74

 anew

-0.72

azel

-0.71

NB

-0.68

entimes

-0.67

elman

-0.67

perm

-0.66

dar

-0.66

POSITIVE LOGITS

 sexes

1.47

 ages

0.92

 extremes

0.91

 genders

0.89

 aforementioned

0.87

 parties

0.84

 respective

0.83

 latter

0.82

 factions

0.81

two

0.77

Activations Density 0.072%

phrases indicating a comparison or relationship between different entities or concepts

the word "the" and its variations in different contexts

No Comments

No Known Activations