INDEX

Explanations

terms related to change or transformation

oai_token-act-pair · gpt-3.5-turbo

words related to change and transformation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Borders

-0.72

 Physicians

-0.71

 Outdoor

-0.70

 Antiqu

-0.69

©¶æ

-0.69

PLIED

-0.68

çĶ°

-0.67

RAY

-0.67

VERTIS

-0.67

 outpatient

-0.65

POSITIVE LOGITS

 chang

1.13

eless

0.93

xual

0.84

artz

0.82

eto

0.76

ues

0.76

eter

0.75

het

0.75

ials

0.73

eme

0.73

Activations Density 0.013%

terms related to change or transformation

words related to change and transformation

No Comments

No Known Activations