INDEX

Explanations

positive words related to virtues or benefits

oai_token-act-pair · gpt-3.5-turbo

references to positive qualities or actions

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

eters

-0.79

ptin

-0.73

 Pavilion

-0.71

kson

-0.71

ocene

-0.70

pper

-0.70

âĹ¼

-0.67

pora

-0.67

eteria

-0.67

 Strait

-0.66

POSITIVE LOGITS

enough

1.21

reads

1.07

 Samar

1.00

 luck

0.99

 deed

0.96

 intentions

0.96

 deeds

0.93

NESS

0.87

sword

0.87

ol

0.87

Activations Density 0.069%

positive words related to virtues or benefits

references to positive qualities or actions

No Comments

No Known Activations