INDEX

Explanations

words related to simplification and efficiency

oai_token-act-pair · gpt-3.5-turbo

words related to the concept of simplification

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

rings

-0.70

PAR

-0.70

lord

-0.68

wine

-0.66

affer

-0.66

mal

-0.65

PU

-0.65

EP

-0.64

âĻ¦

-0.64

vet

-0.63

POSITIVE LOGITS

 simpl

0.90

 simplify

0.90

 simplified

0.75

 simplicity

0.74

istically

0.73

 Simpl

0.73

hift

0.71

spection

0.67

 Calculator

0.67

veland

0.66

Activations Density 0.026%

words related to simplification and efficiency

words related to the concept of simplification

No Comments

No Known Activations