INDEX

Explanations

mentions of bans on specific activities or objects

oai_token-act-pair · gpt-3.5-turbo

references to prohibitions or restrictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 IMAGES

-0.77

 Generations

-0.76

lycer

-0.67

 Temper

-0.67

 Barg

-0.66

 Apostles

-0.65

 Editors

-0.65

Â¯Â¯

-0.63

 Directions

-0.63

rious

-0.62

POSITIVE LOGITS

ishment

1.22

hammer

1.04

hee

0.96

ishing

0.93

tering

0.90

nered

0.90

zai

0.88

ish

0.87

ished

0.87

icip

0.84

Activations Density 0.026%

mentions of bans on specific activities or objects

references to prohibitions or restrictions

No Comments

No Known Activations