INDEX

Explanations

names of individuals and places

oai_token-act-pair · gpt-3.5-turbo

negative sentiment or criticism

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Dickinson

-0.74

etheless

-0.73

 pause

-0.70

 eternity

-0.67

 shade

-0.65

wcs

-0.64

 diam

-0.63

 todd

-0.63

 VIEW

-0.63

 reflection

-0.63

POSITIVE LOGITS

based

1.14

cert

1.04

san

1.02

sama

1.00

sized

0.98

kun

0.97

derived

0.95

nom

0.95

affiliated

0.95

themed

0.94

Activations Density 0.373%

names of individuals and places

negative sentiment or criticism

No Comments

No Known Activations