INDEX

Explanations

phrases indicating permission or invitation

oai_token-act-pair · gpt-3.5-turbo

phrases encouraging freedom and the invitation to share opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

fam

-0.67

ELD

-0.65

ritical

-0.63

dated

-0.61

quickShipAvailable

-0.60

croft

-0.60

lehem

-0.59

assium

-0.59

iron

-0.59

 Adin

-0.59

POSITIVE LOGITS

 choose

1.14

 roam

1.10

 decide

1.10

 improv

1.05

 experiment

1.01

 pursue

1.00

 criticize

0.98

 explore

0.98

 disagree

0.96

 modify

0.95

Activations Density 0.115%

phrases indicating permission or invitation

phrases encouraging freedom and the invitation to share opinions

No Comments

No Known Activations