INDEX

Explanations

terms related to specific attributes or features

oai_token-act-pair · gpt-3.5-turbo

references to characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

NAS

-0.74

GS

-0.73

kos

-0.68

arger

-0.68

EMS

-0.68

gur

-0.67

aii

-0.67

×Ķ

-0.67

ski

-0.66

BSD

-0.65

POSITIVE LOGITS

 characteristics

1.06

istics

1.06

 traits

0.98

Features

0.85

ively

0.84

eatures

0.83

 charact

0.83

 similarities

0.81

 guiActiveUn

0.80

 qualities

0.79

Activations Density 0.012%

terms related to specific attributes or features

references to characteristics

No Comments

No Known Activations