INDEX

Explanations

adjectives describing the size or extent of something

oai_token-act-pair · gpt-3.5-turbo

phrases that begin with "such a" followed by varying descriptions or attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Annotations

-0.70

 ensu

-0.70

 Airl

-0.67

 RCMP

-0.66

 Uriel

-0.66

 Jagu

-0.65

 Palest

-0.65

 srfAttach

-0.65

 Pigs

-0.65

 Polo

-0.62

POSITIVE LOGITS

 thing

0.98

ãĥĥãĥĪ

0.79

 bunch

0.79

 scenario

0.77

complex

0.76

fecture

0.75

omination

0.75

uncture

0.74

 delicate

0.73

rouse

0.72

Activations Density 0.045%

adjectives describing the size or extent of something

phrases that begin with "such a" followed by varying descriptions or attributes

No Comments

No Known Activations