INDEX

Explanations

names or titles, specifically those related to professions or positions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating roles or positions within organizations or departments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

aan

-0.77

mort

-0.75

BR

-0.74

llah

-0.69

JV

-0.68

 gorge

-0.68

 danced

-0.67

ptions

-0.65

Driver

-0.64

isphere

-0.64

POSITIVE LOGITS

geries

0.96

bidden

0.85

 whom

0.83

gery

0.79

 example

0.78

 Horizon

0.77

 Borderlands

0.77

 instance

0.76

gotten

0.76

aging

0.75

Activations Density 0.087%

names or titles, specifically those related to professions or positions

phrases indicating roles or positions within organizations or departments

No Comments

No Known Activations